As much as people on Hacker News complain about subscription models for productivity and creativity suites, the open arms embrace of subscription development tools (services, really) which seek to offload the very act itself makes me wonder how and why so many people are eager to dive right in. I get it. LLMs are cool technology.
Is this a symptom of the same phenomenon behind the deluge of disposable JavaScript frameworks of just ten years ago? Is it peer pressure, fear of missing out? At its root, I suspect so; of course I would imagine it's rare for the C-suite to have ever mandated the usage of a specific language or framework, and LLMs represent an unprecedented lever of power to have an even bigger shot at first mover's advantage, from a business perspective. (Yes, I am aware of how "good enough" local models have become for many.)
I don't really have anything useful nor actionable to say here regarding this dialling back of capability to deal with capacity issues. Are there any indications of shops or individual contributors with contingency plans on the table for dialling back LLM usage in kind to mitigate these unknowns? I know the calculus is such that potential (and frequently realised) gains heavily outweigh the risks of going all in, but, in the grander scheme of time and circumstance, long term commitments are starting to be more apparently risky. I am purposefully trying to avoid "begging the question" here; if instead of LLMs, this were some other tool or service, reactions to these events would have been far more pragmatic, with less of a reticence to invest time on in-house solutions when dealing with flaky vendors.
HN is a big community that has always had a mix of people who value newness as a feature vs those who prioritize simplicity and reliability. Unless you're recognizing the exact same names taking these contradictory opinions it's probably different groups of people for the most part.
It seems like every LLM thread for the past couple years is full of posts saying that the latest hot AI tool/approach has made them unbelievably more productive, followed by others saying they found that same thing underwhelming.
I don't think many of you have legitimately tried Claude Code, or maybe you're holding it wrong.
I'm getting 10x the work done. I'm operating at all layers of the stack with a speed and rapidity I've never had before.
And before anyone accuses me of being some "vibe coder", I've built five nines active-active money rails that move billions of dollars a day at 50kqps+, amongst lots of other hard hitting platform engineering work. Serious senior engineering for over a decade.
This isn't just a "cool technology". We've exited the punch card phase. And that is hard or impossible to come back from.
If you're not seeing these same successes, I legitimately think you're using it wrong.
I honestly don't like subscription services, hyperscaler concentration of power, or the fact I can't run Opus locally. But it doesn't matter - the tool exists in the shape it does, and I have to consume it in the way that it's presented. I hope for a different offering that is more democratic and open, but right now the market hasn't provided that.
It's as if you got access to fiber or broadband and were asked to go back to ISDN/dial up.
Man I really thought this was satire. It’s phenomenal that you can gain 10x benefits at all layers of the stack, you must have a very small development team or work alone.
I just don’t see how I could export 10x the work and have it properly validated by peers at this point in time. I may be able to generate code 10-20x faster, but there are nuances that only a human can reason about in my particular sector.
Senior engineer with 25 years of experience here. I wish I spent enough time actually coding that 10x-ing my coding productivity would matter much to my job. Most of my day is spent wrangling requirements, looking after junior devs, stamping out confusion brush fires before they get out of control, and generally just trying to steer the app away from a trainwreck down the line.
When I do code, it's almost always something novel that I don't know how I'm going to implement until I code a few pieces and see how they fit together. If it's a fairly routine feature based on an existing pattern, I assign it to one of the other devs.
This is basically the thing I keep coming back to with the agentic tools.
It is the wrangling requirements, stamping out confusion, and steering away from a trainwreck down the line that are the actual challenging parts of the job and we can't automate those yet. Once you do actually know the code change you want to make though it is pretty nice to change it 10x faster than before.
> I just don’t see how I could export 10x the work and have it properly validated by peers at this point in time.
In my experience, the people who 10X their output with Claude Code fit one of two categories:
1. They're not really taking the time to understand the code they're submitting. They might do a skim over the output and see that it looks reasonable and passes tests, but they aren't taking time to understand the code as if they were pair programming. Only when it breaks and the LLM can't patch it up quickly do they go in and fully understand the code.
2. They moved very slowly before Claude Code. I've had some coworkers who would take 2-3 days to get a simple PR out because, to be frank, their work days weren't full of a lot of work. Every time they'd run into a question they'd stop and then bumble around for a few hours until they could talk to the ticket creator about it. They'd get tired of working on a task by 2PM and then save the rest of the work for tomorrow. They'd get an idea and decide to rewrite the PR the next day, and on and on with distractions. When they start using Claude Code the LLM doesn't have the same holdups, so now every time where they were getting stuck or tired before is replaced by an LLM powering through to some solution. Their cognitive load is reduced so they're no longer freezing up during the day. They aren't really becoming 10X engineers like they think, but really just catching up to normal pace
I don't know if we're all 10x'ing but our entire org is shipping PRs using an in-house framework akin to Stripe's Minions [1] and many of those PRs are generated from Slack. We definitely have work to do on the latter part of the SDLC to have more confidence in these changes but we can still rely on the existing observability layer to make sure things are working as expected.
Another commenter mentioned that Docker, git, etc. were all tools that greatly enhanced productivity and coding agents are just another tool that does that. I would agree, but argue that it's more impactful than all of those tools combined.
Regarding point #2, while it is of course entirely possible that they are slackers it is more likely that they lack the knowledge you are leveraging in order to declare that the PRs are "simple"
I see some confusion from your downvotes. Sean cited the start of "navy seal copypasta"
The Navy Seal copypasta is a internet meme consisting of an absurdly over the top tough guy threat, posted to mock someone who is acting somehow aggressive, insecure, or self important online, usually after a minor argument.
Here it's full text:
>What the fuck did you just fucking say about me, you little bitch? I'll have you know I graduated top of my class in the Navy Seals, and I've been involved in numerous secret raids on Al-Quaeda, and I have over 300 confirmed kills. I am trained in gorilla warfare and I'm the top sniper in the entire US armed forces. You are nothing to me but just another target. I will wipe you the fuck out with precision the likes of which has never been seen before on this Earth, mark my fucking words. You think you can get away with saying that shit to me over the Internet? Think again, fucker. As we speak I am contacting my secret network of spies across the USA and your IP is being traced right now so you better prepare for the storm, maggot. The storm that wipes out the pathetic little thing you call your life. You're fucking dead, kid. I can be anywhere, anytime, and I can kill you in over seven hundred ways, and that's just with my bare hands. Not only am I extensively trained in unarmed combat, but I have access to the entire arsenal of the United States Marine Corps and I will use it to its full extent to wipe your miserable ass off the face of the continent, you little shit. If only you could have known what unholy retribution your little "clever" comment was about to bring down upon you, maybe you would have held your fucking tongue. But you couldn't, you didn't, and now you're paying the price, you goddamn idiot. I will shit fury all over you and you will drown in it. You're fucking dead, kiddo.
I use Claude Code a lot, but I don't understand these "I'm doing 10X the work" comments.
I spend a lot of time reviewing any code that comes out of Claude Code. Even using Opus 4.6 with max effort there is almost always something that needs to be changed, often dramatically.
I can see how people go down the path of thinking "Wow, this code compiles and passes my tests! Ship it!" and start handing trust over to Opus, but I've already seen what this turns into 6 months down the road: Projects get mired down in so much complexity and LLM spaghetti that the codebase becomes fragile. Everyone is sidetracked restructuring messy code from the past, then fighting bugs that appear in the change.
I can believe some of the more recent studies showing LLMs can accelerate work by circa 20% (1.2X) because that's on the same order of magnitude that I and others are seeing with careful use.
When someone comes out and claims 10X more output, I simply cannot believe they're doing careful engineering work instead of just shipping the output after a cursory glance.
I find that it's relative to the amount of planning time you spend... I feel like I've gotten around 5x the output while using Claude Code w/ Opus over what I will get done myself... That said, I'm probably spending about 3x as much time planning as I would when just straight coding for/by myself. And that's generally the difference.
I can use the agent to scaffold a lot of test/demo frameworks around the pieces I'm working on pretty cleanly and have the agent fill in. I still spend a lot of time validating the tests and the code being completed though.
The errors I tend to get from the agent are roughly similar to what I might see from a developer/team that works remotely... you still need to verify. The difference is the turn around seems to be minutes over days. You're also able to observe over simply review... When I see a bad path, I can usually abort/cancel, revert back to the last commit and try again with more planning.
That's part of why I don't get AI for directly writing code at all. If I am going to be reviewing anything that comes out of it (and I will) then I might as well just write it myself. It's easier and faster, although it does also make it easier to fall victim to blind spots.
You're still manually posting? All of my HN posting, trolling, shitposting and spamming is taken care of by a fleet of bots I vibecoded in the last 5 minutes.
Mind if I use this as a copypasta for the future? This checks off every point people bring on LinkedIn and elsewhere.
In all seriousness though, writing code, or even sitting down and properly architecting things, have never been bottlenecks for me. It has either been artificial deadlines preventing me from writing proper unit tests, or the requirement for code review from people on my team who don't even work on the same codebase as I do on a daily basis. I have often stated and stand by the assertion that I develop at the speed of my own understanding, and I think that is a good virtue to carry forth that I think will stand the test of time and bring about the best organisational outcomes. It's just a matter of finding the right place that values this approach.
Edit for context: My team is an ops team that needed a couple developers; I was picked to implement some internal tooling. The deadlines I was given for the initial development are tied directly to my performance evaluation. My boss has only ever been a manager for almost two years. He has only ever had development headcount for less than a year. He has never been on a development team himself. The man does not take breaks and micromanages at every opportunity he gets. He is paranoid for his job, thinking he is going to be imminently replaced by our (cheaper) EU counterparts. His management style and verbal admonitions reflect this; he frequently projects these insecurities onto others, using unnecessarily accusatory speech. I am not the only developer on my team who has had such interactions with him. I have screenshots of conversations with him that I felt necessary to present to a therapist. This degree of time pressure is entirely unprecedented in my 20 year career. Yes, this is a dysfunctional environment.
> artificial deadlines preventing me from writing proper unit tests, or the requirement for code review from people on my team who don't even work on the same codebase as I do on a daily basis
I have never experienced this, and it sounds remarkably dysfunctional to me.
Believe me, it is very dysfunctional. As I've mentioned to your first replyer, my boss has only had developers for less than a year. This is an operations team I was assigned to in order to provide them some much needed tooling. The pressure my boss has perceived from above has led to my own significant burnout. The guy does not take days off and has always been logged into Slack on the odd hours I would need to pull up some HR form or another. I am currently off work for several months dealing with the fallout from all that.
I've tried everything I can to cope and am not sure I will be willing to return to that team once I am past my medical leave.
Beg pardon? I've been doing this for 20 years. My boss has been a boss for two years and has only had developer headcount for less than a year. This degree of pressure is unprecedented in my career.
It’d be cool to see your process in depth. You should record some of your sessions :)
I mostly believe you. I have seen hints of what you are talking about.
But often times I feel like I’m on the right track but I’m actually just spinning when wheels and the AI is just happily going along with it.
Or I’m getting too deep on something and I’m caught up in the loop, becoming ungrounded from the reality of the code and the specific problem.
If I notice that and am not too tired, I can reel it back in and re-ground things. Take a step back and make sure we are on reasonable path.
But I’m realizing it can be surprisingly difficult to catch that loop early sometimes. At least for me.
I’ve also done some pretty awesome shit with it that either would have never happened or taken far longer without AI — easily 5x-10x in many cases. It’s all quite fascinating.
Much to learn. This idea is forming for me that developing good “AI discipline” is incredibly important.
P.s. sometimes I also get this weird feeling of “AI exhaustion”. Where the thought of sending another prompt feels quite painful. The last week I’ve felt that a lot.
P.p.s. And then of course this doesn’t even touch on maintaining code quality over time. The “after” part when the LLM implements something. There are lots of good patterns and approaches for handling this, but it’s a distinct phase of the process with lots of complexities and nuances. And it’s oh-so-temping to skip or postpone. More so if the AI output is larger — exactly when you need it most.
I mean at this point can we just conclude that there are a group of engineers who claim to have incredible success with it and a group that claim it is unreliable and cannot be trusted to do complex tasks.
I struggle to believe that a ton of seemingly intelligent software engineers are too dumb to figure out how to use Claude code to get reliable results, it seems much more likely to me that it can do well at isolated tasks or new projects but fails when pointed at large complex code bases because it just... is a token predictor lol.
But yeah spinning up a green fields project in an extensively solved area (ledgers) is going to be something an AI shines at.
It isn't like we don't use this stuff also, I ask Cursor to do things 20x a day and it does something I don't like 50% of the time. Even things like pasting an error message it struggles with. How do I reconcile my actual daily experience with hype messages I see online?
Right, I keep seeing people talking past each other in this same way. I don't doubt folks when they say they coded up some greenfield project 10x faster with Claude, it's clearly great at many of those tasks! But then so many of them claim that their experience should translate to every developer in every scenario, to the point of saying they must be using it wrong if they aren't having the same experience.
Many software devs work in teams on large projects where LLMs have a more nuanced value. I myself mostly work on a large project inside a large organization. Spitting out lines of code is practically never a bottleneck for me. Running a suite of agents to generate out a ton of code for my coworkers to review doesn't really solve a problem that I have. I still use Claude in other ways and find it useful, but I'm certainly not 10x more productive with it.
> But yeah spinning up a green fields project in an extensively solved area (ledgers) is going to be something an AI shines at.
I couldn't disagree with this more. It's impressive at building demos, but asking it to build the foundation for a long-term project has been disastrous in my experience.
When you have an established project and you're asking it to color between the lines it can do that well (most of the time), but when you give it a blank canvas and a lot of autonomy it will likely end up generating crap code at a staggering pace. It becomes a constant fight against entropy where every mess you don't clean up immediately gets picked up as "the way things should be done" the next time.
Before someone asks, this is my experience with both Claude Code (Sonnet/Opus 4.6) and Codex (GPT 5.4).
I suspect many people here have tried it, but they expected it to one-shot any prompt, and when it didn't, it confirmed what they wanted to be true and they responded with "hah, see?" and then washed their hands of it.
So it's not that they're too stupid. There are various motivations for this: clinging on to familiarity, resistance to what feels like yet another tool, anti-AI koolaid, earnestly underwhelmed but don't understand how much better it can be, reacting to what they perceive to be incessant cheerleading, etc.
It's kind of like anti-Javascript posts on HN 10+ years ago. These people weren't too stupid to understand how you could steelman Node.js, they just weren't curious enough to ask, and maybe it turned out they hadn't even used Javascript since "DHTML" was a term except to do $(".box").toggle().
Hypothetically, you have a simple slice out of bounds error because a function is getting an empty string so it does something like: `""[5]`.
Opus will add a bunch of length & nil checks to "fix" this, but the actual issue is the string should never be empty. The nil checks are just papering over a deeper issue, like you probably need a schema level check for minimum string length.
At that point do you just tell it like "no delete all that, the string should never be empty" and let it figure that out, or do I basically need to pseudo code "add a check for empty strings to this file on line 145", or do I just YOLO and know the issue is gone now so it is no longer my problem?
My bigger point is how does an LLM know that this seemingly small problem is indicative of some larger failure, like lets say this string is a `user.username` which means users can set their name to empty which means an entire migration is probably necessary. All the AI is going to do is smoosh the error messages and kick the can.
I have encountered the exact same kind of frustration, and no amount of prompting seems to prevent it from "randomly" happening.
`the error is on line #145 fix it with XYZ and add a check that no string should ever be blank`
It's the randomness that is frustrating, and that the fix would be quicker to manually input that drives me crazy. I fear that all the "rules" I add to claude.md is wasting my available tokens it won't have enough room to process my request.
Yup, this is why i firmly believe true productivity, as in, it aiding you to make you faster, is limited by the speed of review.
I think Claude makes me faster, but the struggle is always centered around retaining own context and reviewing code fully. Reviewing code fully to make sure it’s correct and the way I want it, retaining my own context to speed up reviews and not get lost.
I firmly believe people who are seeing massive gains are simply ignoring x% lines of code. There’s an argument to be made for that being acceptable, but it’s a risk analysis problem currently. Not one I subscribe to.
Use planning+execution rather than one-shotting, it'll let you push back on stuff like this. I recommend brainstorming everything with https://github.com/obra/superpowers, at least to start with.
Then work on making sure the LLM has all the info it needs. In this example it sounds like perhaps your hypothetical data model would need to be better typed and/or documented.
But yeah as of today it won't pick up on smells as you do, at least not without extra skills/prompting. You'll find that comforting or annoying depending on where you stand...
Always start an implementation in Claude Code plan mode. It's much more comprehensive than going straight to impl. I never read their prompt for plan mode before, but it deep-dives the code, peripheral files, callsites, documentation, existing tests, etc.
You get a better solution but also a plan file that you can review. And, also important, have another agent review. I've found that Codex is really good at reviewing plans.
I have an AGENTS.md prompt that explains that plan file review involves ranking the top findings by severity, explaining the impact, and recommending a fix to each one. And finally recommend a simpler directional pivot if one exists for the plan.
So, start the plan in Claude Code, type "Review this plan: <path>" in Codex (or another Claude Code agent), and cycle the findings back into Claude Code to refine the plan. When the plan is updated, write "Plan updated" to the reviewer agent.
You should get much better results with this capable of much better arch-level changes rather than narrow topical solutions.
If that's still not working sufficiently for you, maybe you could use more support, like a type-system and more goals in AGENTS.md?
IMO, plan mode is pretty useless. For bug fixes and small improvements, I already know where to edit (and can do it quickly with vim-fu).
For new features, I spend a bit of time thinking, and I can usually break it down in smaller tasks that are easy to code and verify. No need to wrangle with Plan mode and a big markdown file.
I can usually get things one-shotted by that point if I bother with the agent.
My manager and I have been experimenting with it for some stuff, and our most recent attempt at using plan mode was a refactor to change a data structure and make some conversion code unnecessary, then delete it. The plan looked fine, but after it ran the data structure change was incomplete, most of the conversion code was still there, and it introduced several bugs by changing lines it shouldn't have touched at all. Also removed several "why" style comments and arbitrarily changed variable names to be less clear in code it otherwise didn't change.
This was the costliest one we had access to, chosen as an experiment - took $20 over almost a half hour to run.
Not the person you're replying to but yes, sometimes I do tell the agent to remove the cruft. Then I back up a few messages in the context and reword my request. Instead of just saying "fix this crash", or whatever, I say "this is crashing because the string is empty, however it shouldn't be empty, figure out why it's empty". And I might have it add some tests to ensure that whatever code is not returning/passing along empty strings.
1. I'm working in Rust, so it's a very safe and low-defect language. I suspect that has a tremendous amount to do with my successes. "nulls" (Option<T>) and "errors" (Result<T,E>) must be handled, and the AST encodes a tremendous amount about the state, flow, and how to deal with things. I do not feel as comfortable with Claude Code's TypeScript and React outputs - they do work, but it can be much more imprecise. And I only trust it with greenfield Python, editing existing Python code has been sloppy. The Rust experience is downright magical.
2. I architecturally describe every change I want made. I don't leave it up to the LLM to guess. My prompts might be overkill, but they result in 70-80ish% correctness in one shot. (I haven't measured this, and I'm actually curious.) I'll paste in file paths, method names, struct definitions and ask Claude for concrete changes. I'll expand "plumb foo field through the query and API layers" into as much detail as necessary. My prompts can be several paragraphs in length.
3. I don't attempt an entire change set or PR with a single prompt. I work iteratively as I would naturally work, just at a higher level and with greater and broader scope. You get a sense of what granularity and scope Claude can be effective at after a while.
You can't one shot stuff. You have to work iteratively. A single PR might be multiple round trips of incremental change. It's like being a "film director" or "pair programmer" writing code. I have exacting specifications and directions.
The power is in how fast these changes can be made and how closely they map to your expectations. And also in how little it drains your energy and focus.
This also gives me a chance to code review at every change, which means by the time I review the final PR, I've read the change set multiple times.
“I struggle to believe that a ton of seemingly intelligent software engineers are too dumb to figure out how to use Claude code to get reliable results”
Seemingly is doing the heavy lifting here. If you read enough comment threads on HN, it will become obvious why they aren’t getting results.
> I struggle to believe that a ton of seemingly intelligent software engineers are too dumb to figure out how to use Claude code to get reliable results.
They're not dumb, but I'm not surprised they're struggling.
A developer's mindset has to change when adding AI into the mix, and many developers either can’t or won’t do that. Developers whose commits that look something like "Fixed some bugs" probably aren’t going to take the time to write a decent prompt either.
Whenever there's a technology shift, there are always people who can't or won't adapt. And let's be honest, there are folks whose agenda (consciously or not) is to keep the status quo and "prove" that AI is a bad thing.
No wonder we're seeing wildly different stories about the effectiveness of coding agents.
Here's my 100 file custom scaffolding AI prompt that I've been working on for the last four months, and can reliably one-shot most math olympic problems and even a rust to do list.
I see two basic cases for the people who are claiming it is useless at this point.
One is that they tried AI-based coding a year or two ago, came to the IMHO completely correct at that time conclusion that it was nearly useless, and have not tried it since then to see that the situation has changed. To which the solution is, try it again. It changed a lot.
The other are those who have incorporated into their personal identity that they hate AI and will never use it. I have seen people do things like fire AI at a task they have good reasons to believe it will fail at, and when it does, project that out to all tasks without letting themselves consciously realize that picking a bad task on purpose skews the deck.
To those people my solution is to encourage them to hold on to their skepticism. I try to hold on to it as well despite the incredible cognitive temptation not to. It is very useful. But at the same time... yeah, there was a step change in the past year or so. It has gotten a lot more useful...
... but a lot of that utility is in ways that don't obviate skilled senior coding skills. It likes to write scripting code without strong types. Since the last time I wrote that, I have in fact used it in a situation where there were enough strong types that it spontaneously originated some, but it still tends to write scripting code out of that context no matter what language it is working in. It is good at very straight-line solutions to code but I rarely see it suggest using databases, or event sourcing, or a message bus, or any of a lot of other things... it has a lot of Not Invented Here syndrome where it instead bashes out some minimal solution that passes the unit tests with flying colors but can't be deployed at scale. No matter how much documentation a project has it often ends up duplicating code just because the context window is only so large and it doesn't necessarily know where the duplicated code might be. There's all sorts of ways it still needs help to produce good output.
I also wonder how many people are failing to prompt it enough. Some of my prompts are basically "take this and do that and write a function to log the error", but a lot of my prompts are a screen or two of relevant context of the project, what it is we are trying to do, why the obvious solution doesn't work, here's some other code to look at, here's the relevant bugs and some Wiki documentation on the planning of the project, we should use {event sourcing/immutable trees/stored procedures/whatever}, interact with me for questions before starting anything. This is not a complete explanation of what they are doing anymore, but there's still a lot of ways in which what an LLM can really do is style transfer... it is just taking "take this and do that and write a function to log the error" and style-transforming that into source code. If you want it to do something interesting it really helps to give it enough information in the first place for the "style transfer" to get a hold of and do something with. Don't feel silly "explaining it to a computer", you're giving the function enough data to operate on.
I can see huge utility with AI as a guide and helper.
But not being one leg in the code myself is not something I am comfortable with. It starts feeling like management and not development. I really feel the abdication very strongly and it makes me unable and unwilling to put a hard stamp on quality. I have seen too much hallucination or half missed requirements to put that much trust in AI.
It's the same with code reviews of hard tickets. You can scroll past and just approve, but do you really understand what your colleague has built? Are you really in the driver's seat? It feels to me like YOLOing with major consequences.
I dont but, at all that people doing 20x output have any idea what they are coding. They are just pressing the yolo button and no one, not the engineer, not the AI and not management is in the driver's seat. it is a very scary time.
I'm still reviewing all the code that's created, and asking for modifications, and basically using LLMs as a 2000 wpm typist, and seeing similar productivity gains. Especially in new frameworks! Everything is test driven development, super clean and super fast.
The challenge now is how to plan architectures and codebases to get really big and really scale, without AI slop creating hidden tech debt.
Foundations of the code must be very solid, and the architecture from the start has to be right. But even redoing the architecture becomes so much faster now...
I don't want to sound like I'm trying to one-up you, but I've basically vibe coded the entire internet.
I'm surprised nobody thought of it before me but basically the LLM's are trained on the internet and I just had it spit back out everything.
It's running in parallel so I can validate it, which of course I'm using LLM's to do that.
Once it's ready I will put it on the market, but get this, my internet will be cheaper than the current internet. I'll probably just make it one cheaper, like if the current internet costs, for example, 7, I'll make my internet cost 6.
> and I have to consume it in the way that it's presented
I'm just curious, why do you "have to"? Don't get me wrong, I'm making the same choice myself too, realizing a bunch of global drawbacks because of my local/personal preference, but I won't claim I have to, it's a choice I'm making because I'm lazy.
What are the reasonable options besides a Claude Code subscription (or an equivalent from Codex or Copilot)?
I could pay API prices for the same models, but aside from paying much more for the same result that doesn't seem helpful
I could pay a 4-5 figure sum for hardware to run a far inferior open model
I could pay a six figure sum for hardware to run an open model that's only a couple months behind in capability (or a 4-5 figure sum to run the same model at a snail's pace)
I could pay API costs to semi-trustworthy inference provider to run one of those open models
None of those seem like great alternatives. If I want cutting-edge coding performance then a subscription is the most reasonable option
Note that this applies mostly to coding. For many other tasks local models or paid inference on open models is very reasonable. But for coding that last bit of performance matters
As a professional you have a choice in how you produce whatever it is you produce. Sure, you can go for the simplest, most expensive and "easiest" way of doing things, or you can do other things, depending on your perspective and requirements. None of this is set in stone, some people make choices based on personal preferences, and that matters as much to them as your choices matter to you.
> And before anyone accuses me of being some "vibe coder", I've built five nines active-active money rails that move billions of dollars a day at 50kqps+, amongst lots of other hard hitting platform engineering work. Serious senior engineering for over a decade
You sound like a pro wrestler. I'd like to know what "hard-hitting" engineering work is. Hydraulic hammers?
I mean five nines is legitimately difficult to accomplish for a lot of problem spaces.
It's also like.... difficult to honestly and accurately measure. And account for whether or not you're getting lucky based on your underlying dependencies (servers, etc) not crashing as much as advertised, or if it's actually five nines. Or whether you've run it for a month and gotten <30s of measure downtime and declared victory, vs run it for three years with copious software updates.
I always assume most people claiming five nines are just not measuring it correctly, or have not exercised the full set of things that will go wrong over a long enough period of time (dc failures, network partitions, config errors, bad network switches that drop only UDP traffic on certain ports, erroneous ACL changes, bad software updates, etc etc)
Maybe they did it all correct though, in which case, yea, seems hard hitting to me.
> the open arms embrace of subscription development tools (services, really) which seek to offload the very act itself makes me wonder how and why so many people are eager to dive right in
Here's a reason not in your list.
Short version: A kind of peer pressure, but from above. In some circles I'm told a developer must have AI skills on their resume now, and those probably need to be with well known subscription services, or they substantially reduce their employment prospects.
Multiple people I know who are employers have recently, without prompting, told me they no longer hire developers who don't use AI in their workflow.
One of them told me all the employers they know think "seniors" fall into two camps, those who are embracing AI and therefore nimble and adaptive, and those who are avoiding it and therefore too backward-looking, stuck-in-their-ways to be a good hire for the future. So if they don't see signs of AI usage on a senior dev's resume now, that's an automatic discard. For devs I know laid off from an R&D company where AI was not permitted for development (for IP/confidentiality reasons), that's unfair as they were certainly not backward-looking people, but the market is not fair.
Another "business leader" employer I met recently told me his devs are divided into those who are embracing AI and those who aren't, said he finds software feature development "so slow!", and said if it wasn't for employment law he'd fire all his devs who aren't choosing to use AI. I assume he was joking, but it was interesting to hear it said out loud without prompting.
I've been to several business leadership type meetups in recent months, and it seems to be simply assumed that everyone is using AI for almost everything worth talking about. I don't think they really are, so it's interesting to watch that narrative playing out.
Apart from local AI, a serious choice is aggregated API such as new-api [0]. An API provider aggregated thousands of accounts has much better stability than a single account. It's also cheaper than the official API because of how the subscription model works, see e.g. the analysis [1].
You don't even need to be a customer served by Anthropic or OpenAI so the Terms of Service are irrelevant. That's how I live in China and use almost free Claude and GPT which they don't sell here.
Wait, is this just something like openrouter, that routes your requests to different API providers, where you're paying per-token rates? Or is this taking advantage of fixed price plans, by offering an API interface for them, even though they're only supposed to be used with the official tools?
The whole point of these services is that it’s not your account. It’s very much anthropic’s problem, and honestly I don’t care they’re getting ripped off.
I think some workflows are just that much faster with AI. And if not I can spare the time for a prompt to get work done in parallel to the stuff I work on.
There is a cost though, the context switches of topics aren't free. But if I need to visualise a something, I let an LLM create a page. If I have two tables of data that needs to be joined/mapped, I let an LLM do the first shot, often that is enough.
I cannot even hope to reach that speed. It isn't a magic tool, but it really accelerates some task.
That speed allows for in-house solutions to become viable again, software that really adapts specific business processes instead of some wonky ERP package that never really fit what you were trying to do.
I have our dbs schema checked into a Gitea repository, which our AIs can just access to quickly ingest schema definitions. If data safety is an issue, use a local model. It is extremely beneficial if you quickly can establish context and let your AI deal with real problems. And it is quite good at that.
I really enjoy coding. I've build a number of projects, personal and professional, with Python, Rust, Java and even some Scala in the mix. However, I've been addicted to Claude Code recently, especially with the superpowers skill. It feels like I can manifest code with my mind. When developing with Claude, I am presented with design dilemmas, architectural alternatives, clarification questions, things that really make me think about the problem. I then choose a solution, propose alternatives, discuss, and the code manifests. I came to realize that I enjoy the problem solving, not the actual act of writing the code. Like I have almost cloned my self, and my clones are working on the projects and coming back to me for instructions. It feels amazing
"Addicted" "Superpowers" "manifest with my mind" "it feels amazing"
Why does it sound like you're on drugs? I know that sounds extremely rude, but I can't think of any other reasonable comparison for that language.
It's hard to take these kinds of endorsements seriously when they're written so hyperbolically, in terms of the same cliches, and focused on entirely on how it makes you feel rather than what it does.
Reading a bunch of posts related to Claude Code and some folks voice genuine upset about rate limits and model intelligence while others seem very upset they can't get their fix because they've reached the five hours limits is genuinely concerning to how addictive LLMs can be for some folks.
I think the social aspect is underreported. I think this applies even for people using Claude Code and not just those treating an LLM as a therapist. In other words, I wonder how many of these people can't call their doctor to make an appointment or call a restaurant to order a pizza. And I say this as someone who struggles to do those things.
People claim that DoorDash and other similar apps are about efficiency, but I suspect a large portion is also a desire to remove human interaction. LLMs are the same. Or, in actuality, to create a simulacrum of human interaction that is satisfying enough.
It's reflecting the value we get from it, relative to the cost of continuing if we switch to the API pricing. It is genuinely upsetting to hit the limits when you face a substantial drop in productivity.
Imagine being an Uber driver and suddenly have to switch to a rickshaw for several hours.
"superpowers" is the exact name of the specific Claude code skill. The rest of your concerns is just me expressing my excitement, as until recently I was very skeptic of the whole vibe-coding movement, but have since done a complete 180.
The drug is the llm coding. I kind of get it, when I was a kid and first got a computer I felt the same way after I learned assembly language. The world is your oyster and you can do what felt like anything. It was why I spent almost every waking hour working on my computer. That wore off eventually but I've spent some time on my backlog of projects with Claude and it feels bit like the old days again.
> Why does it sound like you're on drugs, specifically cocaine?
This has basically been what all of Silicon Valley sounds like to me for a few years now.
They are known for abusing many psycho-stimulants out there. The stupid “manifesto” Marc Andreessen put out a while back sounded like adderall-produced drivel more than a coherent political manifesto.
If I were to go off into the woods, take a lot of drugs, and write my own crank manifesto, the central conceit would be that ADHD is the key to understanding the entirety of Silicon Valley. A bunch of people with stimulus driven brains creating technologies that feed themselves and the rest of the populace more and more stimulation, setting a new baseline and requiring new technologies for higher levels of stimulation in an endless loop until we all stimulate ourselves to death. Delayed gratification is the enemy.
This is similar to how we have already found hacks in our evolutionary programming to directly deliver high amounts of flavor without nutrition, and we've been working on ever more complex means of delivering social stimulation without the need for other human (one of the key appeals of AI for many people, as well).
Of course these are all the ravings of a crank and should be ignored.
I feel this sentiment. It’s more like pair programming with someone both smarter and dumber than you. If you’re reviewing the code it is putting down, you’re likely to spot what it’s getting wrong and discussing it.
What I don’t understand, are the people who let it go over night or with whole “agent teams” working on software. I have no idea how they trust any of it.
That’s like saying enjoying composing music, but not enjoying playing music. Or creating stories, but don’t like writing. Yes they’re different activities, but linked together. The former is creativity, the latter is a medium of transmission.
Code is notation, just like music sheets, or food recipes. If your interaction with anyone else is with the end result only (the software), the. The code does not matter. But for collaboration, it does. When it’s badly written, that just increase everyone burden.
It’s like forcing everyone to learn a symphony with the record instead of the sheets. And often a badly recorded version.
> That’s like saying enjoying composing music, but not enjoying playing music
Do you think that is impossible? There are plenty of people who enjoy composing music on things like trackers, with no intent of ever playing said music on an instrument.
I love coding, but I also like making things, and the two are in conflict: When I write code for the sake of writing code, I am meticulous and look for perfection. When I make things, I want to move as fast as possible, because it is the end-product that matters.
There is also a hidden presumption in what you've written that 1) the code will be badly written. Sometimes it is, but that is the case for people to, but often it is better than what I would produce (say, when needing to produce something in a language I'm not familiar enough with), 2) and that the collaboration will be with people manually working on the code. That is increasingly often not true.
I struggle to understand that comparison. Code is notation, you can’t write code for the sake of writing code. You have a problem and you instruct the computer how to do it. And for the sake of your collaborator and your futher self, you take care of how you write that. There’s no real distinction IMO.
> There is also a hidden presumption in what you've written that 1) the code will be badly written
The computers does not really care about what programming language you’re using and the name of your variables and other indentifiers. People do. You can have correct code (decompiled assembly or minified JavaScript) and no one will wants to collaborate on that.
Code is often the most precise explanation of some process. By being formal, it’s a truthful representation of the process. Specs and documentations can describe truth, but they do not embody it.
You can always collaborate with markdown files. But eventually someone will have to look at the code and understand what it does, because that’s the truth that matters. Anything else is prayers and hope. And if you’ve never cared about maintainability and quality of the code, it will probably be an arduous process.
> Code is notation, you can’t write code for the sake of writing code.
Of course you can.
> You have a problem and you instruct the computer how to do it.
And sometimes that problem is not the point. Just like sometimes I write for the joy of writing, not because I particularly care about a reader or the meaning of the output.
> The computers does not really care about what programming language you’re using and the name of your variables and other indentifiers. People do. You can have correct code (decompiled assembly or minified JavaScript) and no one will wants to collaborate on that.
This has no relation whatsoever to the sentence you quoted.
> This has no relation whatsoever to the sentence you quoted.
Maybe I wasn’t clear. What I wanted to convey is that the use of programming languages, paradigms, patterns, and other software engineering principles is related to the human side of programming.
You can solve a problem correctly, but with the resulting code being hard to parse. Or you can write readable code but with bugs. And almost everyone prefers the latter.
So badly written means incomprehensible code, mostly due to the size of it in the case of Agents. It’s all right if no one cares about the code. But if you expect someone to review it, changeset that even the author don’t understand is slop.
So again, this presumes that the result must be incomprehensible. That is not at all my experience. It may become incomprehensible if you let it, just as is the case with human developers. It won't be if you enforce reviews, and your harness demands cleanups and sets clear standards.
Using your analogy, I enjoy composing music and enjoy playing music. I don't enjoy going through the notion of writing the notes on a piece of paper with the pen. I have to do it because people can't read my mind, but if they could I would avoid it. Claude code is like that. The code that gets written, feels like the code that I would have written
> if instead of LLMs, this were some other tool or service, reactions to these events would have been far more pragmatic, with less of a reticence to invest time on in-house solutions when dealing with flaky vendors
As an example, a long term goal at the employer I work for is exactly this: run LLMs locally. There's a big infrastructure backlog through, so it's waiting on those things, and hopefully we'll see good local models by then that can do what Claude Sonnet or GPT-5.3-Codex can do today.
Well, I wanted to understand what is this cool new tech everybody is talking about so I bought a Max plan, experimented with various setups recommended by various experts, vibe-coded a few apps and then threw it all away.
I still use more traditional approach for finding bugs and other issues in my code, but the agentic workflow doesn't give me any net value.
People will always go along with a removal of friction even against their benefit. It's natural bias, we have a preference for not spending energy.
It's why we pay stupid amounts for takeout when it's a button away, it's why we accept the issues that come with online dating rather than breaking the ice outside, it's why there's been decades scams that claim to get you abs without effort...
LLMs are the ultimate friction removal. They can remove gaps or mechanical work that regular programming can, but more importantly they can think for you.
I'm convinced this human pattern is as dangerous as addiction. But it's so much harder to fight against, because who's going to be in favor of doing things with more effort rather than less? The whole point of capitalism is supposed to be that it rewards efficiency.
Aw hell. You found my vice and my own cognitive dissonance here. If I want to truly stand by my convictions, I should probably cook more and log off. Waiting for signs that the tides are turning and that people are beginning to value a slower, more methodical approach again isn't doing anything in the current moment to stave off the genuine feelings of dread that have honestly led to some suicidal ideation.
Think of the stupidest product you can think of and you likely only know about it because people buy/bought them en masse. AI is no different from any other product; plenty will pay/adopt for exactly the reasons you said. There is powerful motivations for people to feel “ahead” of others (or more informed, or more “cool”, or more knowledgeable, or more experienced, or whatever their ego requires), even if their situation is exactly the same.
That said, I’m not sure I follow your statement of less resistance to the development of internal tools when the opposite seems to be the case; companies (or more specifically developers) are perhaps too quick to think they can just vibe-code a replacement for any vendor in a weekend these days.
Contingency plan? Just code without it like before. AI could disappear today and I would be very disappointed but it's not like I forgot how to code without it. If anything, I think it's made me a better programmer by taking friction away from the execution phase and giving me more mental space to think in the abstract at times, and that benefit has certainly carried over to my work where we still don't have copilot approved yet.
I would love nothing more than ditching Claude for a local solution tomorrow. But it doesn't exist today, so it is what it is - you gotta keep up with the joneses.
Maybe in 5 years we'll have an open weights model that is in the "good enough" category that I can run on a RTX 9000 for 15k dollars or whatever.
I don't want to get too much into the details but I don't work in or for the Valley and I don't think I'll ever be able to afford that sort of expenditure on computing. A down payment on a car, or a vital medical procedure? Sure. I'm probably not alone here.
I think most people understand the need for subscriptions here. It is an ongoing massive compute cost, and that’s what you’re paying for. Your local system is not capable of running the massive amount of compute required for this. If it were then we would see more people up in arms about it.
We could run it locally, but the problems that matter simply don't change.
We're paying for servers that sit idle at night, you don't find enough sysadmins for the current problems, the open source models aren't as strong as closed source, providing context (as in googling) means you hook everything up to the internet anyway, where do you find the power and the cooling systems and the space, what do you do with the GPUs after 3 years?
The great part is that you can always build your own selfhosted tools. There is nothing that can't be done at home, it's just a calculation of how much you're willing to spend.
Lately though the RAM crisis is continuing and making things like this more unfeasible. But you can still use a lot of smaller models for coding and testing tasks.
Planning tasks I'd use a cloud hosted one, for now, because gemma4 isn't there yet and because the GPU prices are still quite insane.
The cool and fun part is that with ollama and vllm you can just build your own agentic environment IDE, give it the tools you like, and make the workflow however you like. And it isn't even that hard to do, it just needs a lot of tweaking and prompt fiddling.
And on top of that: Use kiwix to selfhost Wikipedia, stackoverflow and devdocs. Give the LLM a tool to use the search and read the pages, and your productivity is skyrocketing pretty quickly. No need anymore to have internet, and a cheap Intel NUC is good enough for self-hosting a lot of containers already.
Source: I am building my own offline agentic environment for Golang [1] which is pretty experimental but sometimes it's also working.
Mounting evidence that claude max users are put into one big compute fuel pool. Demand increased dramatically with OpenAI's DoD PR snafu (even though Anth was already working with the DoD? But I digress...). The pool hit a ceiling. Anth has no compute left to give. Hence people maxing out after 1 query. "Working on it" means finding a way to distill Claude Code that isn't enough of a quality degradation to be noticed[0], in order to get the compute pool operational again. The distillation will continue until uptime improves.
0 as of this writing, it's noticeable. Lots of "should I continue?" And "you should run this command if you want to see that information." Roadblocks that I hadn't seen in a year+
There's another piece of the puzzle. Dario has very clearly stated they are not taking the OpenAI approach of spending $trillion to scale right now and assume the money comes later. They are spending significantly less and working towards profitability sooner.
That means they are going to be far more constrained infrastructurally than some of the competition. I think this is some of the constraints that we are seeing.
He did say that. And, in virtually the same breath, said they would have to spend $trillions if they hope to remain SOTA, which they have to be [0],[1].
They don't have compute because they didn't play the game and get the good rates a couple of years ago, and are now forced to work with third-rate providers. That's not a strategy.
I would take everything he says with a huge grain of salt.
[0] “We’re buying a lot. We’re buying a hell of a lot. We’re buying an amount that’s comparable to what the biggest players in the game are buying.”
“Profitability is this kind of weird thing in this field. I don’t think in this field profitability is actually a measure of spending down versus investing in the business.”
[1] “You don’t just serve the current models and never train another model, because then you don’t have any demand because you’ll fall behind.”
So he's not spending so they can be profitable, AND spending as much as the biggest players are spending, AND not really looking at profit as a measure of anything? K.
I don't think anyone is talking about it because it's not a very productive conversation to have. I'm not particularly bullish on vibe coding either but if you could explain what exactly about vibe coding causes these specific issues then it could be more interesting to discuss.
But as it stands, the more likely reason is capacity crunch caused by a chips shortage and demand heavily outpacing supply. You vibe coding reason is based on as much vibes as their code probably is.
Vibe coding does not usually produce performant code, it produces spaghetti with the goal of making the user asking for work to be done to go away as soon as possible with a (often barely) working solution.
I recently vibe-translated a simple project from Javascript to C, where Javascript was producing 30fps, and the first C version produced 1 frame every 20 seconds. After some time trying to get the AI to optimize it, I arrived at 1fps from the C project. Not a win, but the AI did produce working C code.
I have no doubt that if I had done this myself (which I will do soon), with the appropriate level of care, it would have been 30fps or more.
that is a separate issue indeed, but their comms make it rather obvious they are scrambling to reduce compute and they're just slashing their service selectively - with openclaw and max users being the first in the chopping block
If an AI doesnt generate perfect code, if left to its devices it will at some point create a codebase big and nasty enough that it will not be able to deal with it.
It should catch up faster. It's absolutely useless for the bulk of the tedium—notably, soldering together random repos to satisfy executives—that makes up my job now.
That's not an elephant in the room.. it's just proof of how insanely useful the tool is and the reality that so much more hardware is needed. Thus people saying "why are these companies building insanely large data centers" ... this is why!
The problem is that vibe-coding, when it fails (i.e. it's non-useful, at least for a bit), is usually solved by more vibes. Try again and hope it works. Ask it to refactor and hope the cleaner code helps it along. If you're willing to think about the code yourself you'll likely ask it questions about the codebase. High vibe-code usage is both a metric that it is working and that it's failing.
I think it is telling that this audience down votes this. It's kind of obvious that the thing is being used a lot. Doesn't mean it works as well as advertised. Doesn't mean the business model they have works. Just means there is a lot of demand. You can't ignore that.
I have no particular insight into the Anthropic backend, but it's possible in general for systems to have architectural issues which cannot be mitigated by just adding more hardware.
The proof is already there. It's concrete. I've seen it directly the last few months of using claude code. It closed the loop. It's insanely beneficial when used properly- that is a pure fact. You act like it's an opinion.
Both are great, where they differ is: Claude Code has a better instinct than Codex. Meaning it will naturally produce things like you, the developer, would have.
Codex shines really well at what I call "hard problems." You set thinking high, and you just let it throw raw power at the problem. Whereas, Claude Code is better at your average day-to-day "write me code" tasks.
So the difference is kind of nuanced. You kind of need to use both a while to get a real sense of it.
I think the way I and others use it is code with clause, review or bug hunt with codex. Then I pass the review back to Claude for implementation. Works well. Better than codex implementation and finds gaps versus using Claude to review itself in my opinion.
I'm happy I invested in setting up Codex CLI and getting it to work with ollama. For the toughest jobs I can use Github Copilot (free as an academic) or Gemini CLI. If we see the per token price increase 5x or 10x as these companies move to focusing on revenue, local models will be the way to go, so long as stuff like Gemma 4 keeps getting released.
There was a headline saying they were, and the actual article showed they were doing nothingbof the sort.
If you read HN headlines, and don't even bother to click into the comments and see everyone calling out the headline as bogus, you might think something like your statement is true.
Codex just changed the way they calculate usage with a massive negative impact.
Before a Subscription was the cheapest way to gain Codex usage, but now they've essentially having API and Subscription pricing match (e.g. $200 sub = $200 in API Codex usage).
The only value of a subscription now is that you get the web version of ChatGPT "free." In terms of raw Codex usage, you could just as easily buy API usage.
edit: This is currently rolled out for Enterprise, but is coming to Pro/Plus soon. The people below saying "I haven't had this issue" haven't yet*.
> e.g. $200 sub = $200 in API Codex usage [...] In terms of raw Codex usage, you could just as easily buy API usage.
I don't think it's made out like that, I'm on the ChatGPT Pro plan for personal usage, and for a client I'm using the OpenAI API, both almost only using GPT 5.4 xhigh, done pretty much 50/50 work on client/personal projects, and clients API usage is up to 400 USD right now after a week of work, and ChatGPT Pro limit has 61% left, resets tomorrow.
Still seems to me you'd get a heck more out of the subscription than API credits.
This. ChatGPT Pro personal at $20/month and using GPT 5.4 xhigh is the best deal currently. I don't know if they are actually losing money or betting on people staying well under limits. Clearly they charge extra to businesses on the API plans to make up for it.
In the future, open models and cheaper inference could cover the loss-leading strategies we see today.
Right, because you're on the old and not new structure.
They just rolled it out for new subscribers and existing ones will be getting it in the "coming weeks." Enterprise already got hit with this from my understanding.
I looked at my cc usage and I was at 90% of my weekly allowance after 3 days of use...BUT, if I looked at the usage stats with the chart, it showed, on a scale of 1-4 intensity of usage (4 being most intense), the three days as such:
Day 1: 2
Day 2: 3
Day 3: 1
Not sure how I can hit such limits so quickly with such low scores on its own chart.
Then why not update their chart to at least say that? The numbers (shading, actually) on the chart are not absolute numbers, they're relative, so just make it look as if I spent a lot of time on it. If they're gonna change their limits without being clear about it, at least go all the way. Right now, I can go, "See, you're actually saying I didn't use that much compared to the limits."
I agree; I think that's what happened. But it's a shame—I'm having a lot of trouble with poor-quality results from Claude-Code, and the session limit is being used up quickly.
I assume it's anthropic rejecting the US Government's use of their software for domestic mass surveillance or fully autonomous weapons, and openai happily agreeing to it.
That has led to a significant number of people switching over from openai, or at least stating they were going to do so.
They made a $25 million donation to Trump, which was repaid in kind by designating Anthropic a supply chain risk. Unfortunately, they weren’t nearly subtle enough about this, and went “sure, we’ll take over the contract with no limits on killbots or domestic surveillance, no problem!” on the same day as Anthropic got in trouble, and people put two and two together.
The responsible thing would be to not sell way more subscriptions than their capacity. But they have to show the exponential revenue curves to their investors. I cancelled my subscription yesterday.
Yeah its huge demand upswing from the growth of openclaw and similar pushing resources. Very clear from recent changes and announcement around this [0]
Fwiw there are worse delays from second tier providers like moonshot's kimik2.5 that are also popular for agentic use.
It's also worth keeping in mind that Anthropic's compute needs are nothing like those of a company like Shopify or Adobe, so revenue might not paint accurately enough the picture of what they're dealing with right now.
I assume most of their outages is related to this insane scaling and lack of available compute.
Vibe coding doesn't automatically mean lower quality. My codebase quality and overall app experience has improved since I started using agents to code. You can leverage AI to test as well as write new code.
> I assume most of their outages is related to this insane scaling and lack of available compute.
>
> Vibe coding doesn't automatically mean lower quality
Scalability is a factor of smart/practical architectural decisions. Scalability doesn't happen for free and isn't emergent (the exact opposite is true) unless it is explicitly designed for. Problem is that ceding more of the decision making to the agent means that there's less intentionality in the design and likely a contributor to scaling pains.
My theory is that most of their outages are compute and scale related. IE. A few GPU racks blows out and some customers see errors. They don't have any redundant compute as backup because supply is constrained right now. They're willing to lower reliability to maximize revenue.
This is only true for small companies that can infinitely scale within AWS without anyone noticing.
You are talking about software scaling patterns, Anthropic is running into hardware limitations because they are maxing out entire datacenters. That's not an architectural decision it's a financial gamble to front-run tens of billions in capacity ahead of demand.
Why would you think that the person you are replying to didn't design in scalability? What exactly are emergent features when vibe coding? If scalability is an explicit requirement it can be done.
> What exactly are emergent features when vibe coding?
Regression to the mean. See the other HN thread[0]
The LLM has no concept of "taste" on its own.
Scalability, in particular, is a problem that goes beyond the code itself and also includes decisions that happen outside of the codebase. Infrastructure and "platform" in particular has a big impact on how to scale an application and dataset.
After the CC leak last week I took a look at their codebase and my biggest criticism is they seem to never do refactoring passes.
Personally I write something like 80-90% of my code with agents now but after they finish up, it's critical that you spin up another agent to clean up the code that the first one wrote.
Looking at their code it's clear they do not do this (or do this enough). Like the main file being something like 4000 LOC with 10 different functions all jammed in the same file. And this sort of pattern is all over the place in the code.
I have a buddy who used to work at Shopify and was proud about having sprints dedicated to removing unused features. This is really underrated but is the only reliable way to prevent bloat. Oh and getting rid of bloat is way more satisfying!
I’m sure someone is out there claiming that AI is going to solve all your business’s problems no matter what they are. Remotely sane people are saying it will solve (or drastically improve) certain classes of problems. 3x code? Sure. 3x the physical hardware in a data center? Surely not.
To be clear, this number will probably end up being reasonably accurate, but it is a pet peeve nonetheless in the startup world how shitty these financial metrics have become. We're three months from the end of 2025. You'd think we'd want to see at least two years of $30 billion dollar revenue earned in each year before we say with any meaningful level of statistical validity that they have $30 billion in "annual recurring" revenue.
No one is going to like this answer, but there’s a simple solution: pay for API tokens and adjust your use of CC so that the actions you have it take are worth the cost of the tokens.
It’s great to buy dollars for a penny, but the guy selling em is going to want to charge a dollar eventually…
...pay for API tokens and adjust your use of CC so that the actions you have it take are worth the cost of the tokens
Do you feel there is enough visibility and stability around the "Prompt -> API token usage" connection to make a reliable estimate as to what using the API may end up costing?
Personally, it feels like paying for Netflix based on "data usage" without having anyway for me to know ahead of time how much data any given episode or movie will end up using, because Netflix is constantly changing the quality/compression/etc on the fly.
This reads like even if you had a rough idea today about what usage might look like, a change deployed tomorrow could have a major impact on usage. And you wouldn't know it until after you were already using it.
I'm forced to do this at work. It adjusts the net value to very close to zero. Github's pay per prompt pricing model is phenomenal for users to the point of blowing Anthropic's subscription offering out of the water, much less API pricing. At Copilot pricing, it's quite a useful tool if carefully managed. At API pricing, it's very hard to find a use case for AI.
Of course, I have no idea how MS is justifying the Copilot pricing. I can't imagine any world in which it is sustainable, so I'm trying to get as much as I can out of it now before they jack up prices.
This is it. These subscriptions have been heavily subsidized, which was fine when usage was much lower overall. But with so many folks trying to use the tools and soaking up all the chips something has to give.
Now we’re going to find out what these tools are really worth.
it's not a subsidy. It's predatory pricing and it should be illegal. I offer you a service at a loss to remove competition and then increase prices once you are stuck with it.
I just want a little predictable insight into how much I get. For example, at a buffet, I know I can only eat so much food and can plan around it. This is like going to a buffet and not knowing how many plates I can take or how big the plates are, and it changes each week, and yet I have to keep paying the same price. Except it's not about eating, it's about my work and deadlines and promises and all that.
That's what these providers want as well, but from the other side. They want to know that a customer won't be able to eat more than certain number of servings, as they need to pay for each of those servings.
It works out even if some customers are able to eat a lot, because people on average have a certain limit. The limits of computers are much higher.
Fair, and I think openclaw and all the orchestrators are having agents maxing out the plans. So maybe they figure out a new tier that is agent-run vs human-run. Agents are much more insatiable, whereas humans have a limit. Not sure if it'd be possible to split between those two different modes, but I think that might address the appetite issue better.
I think it would be impossible to find the price point for a monthly subscribtion that would both be profitable to a provider, as well as attractive to the customer. If anything, as the customers would now be paying necessarily even a higher amount for agentic use, they'd make certain they'd be using the agent as effectively as they can, meaning it would be even more costly for the provider.
Pay-per-token is really the only way it can work. If some kind of fixed monthly price is desirable, then there should be a quota the user can assign, and then the agent could e.g. slow itself down by 50% when 50% of the quota is spent, another 50% at 75%, etc, to make it last longer..
As a side thought, I wonder how it could affect an agent's behavior if the information of this token usage/limit was brought to it..
Ironically in chatting with Gemini, helped me realize that telecoms have often solved this problem of unlimited usage with rate/speed limiting. If one goes over 10GB or whatnot of data, then the speed drops from 5G to 3G, and data remains unlimited.
I wonder if there could be something like that, maybe even a progressive rate limiting, where after a certain number of tokens or another metric of use, then the speed slows down a LOT.
Not saying that I would love that as a consumer, as I'd prefer this all-you-can eat, unlimited data plan, but I wonder if that would be a compromise that could work, as it seems to have worked OK with the telecom space.
edit: the nerd in me loves the irony of me making the above comment and then later seeing your username as flux :-)
When you hire a person, you don't know what you are going to get out of them today.
If an hour of an excellent developer's time is worth $X, isn't that the upper bound of what the AI companies can charge? If hiring a person is better value than paying for an AI, then do that.
Fair on not knowing what you'll get out of someone. But if that varies wildly, I may not want to hire that person. Even with employment, predictability matters a lot. If they underperform too much, I might feel annoyed. If they overperform, I might feel guilty.
They can charge whatever they want, I think many people like to make business decisions based on relative predictability or at least be more aware that there's a risk. If they want it to be "some weeks you have lots of usage, some weeks less, and it depends on X factors, or even random factors" then people could make a more informed choice. I think now it's basically incredibly vague and that works while it's relatively predictable, and starts to fail when it's not, for those that wanted the implied predictability.
If you need the tokens for real work, that’s what the API and the other providers like Bedrock are for. The subscription product is merely to whet your appetite.
Well then I would just not use their service. I used extra usage once and just for what I'd consider a low amount of tests and coding, racked up like $300 in an hour or more. For some, that's not a lot of money, for me, I'd just code it manually, especially without knowing almost any way to gauge how much I'll need and how fast it goes.
I'm not sure how businesses budget for llm APIs, as they seem wildly unpredictable to me and super expensive, but maybe I'm missing something about it.
The problem with tokens is that they have wrong incentive. The quicker model arrives at the solution the less tokens you have to buy.
So I noticed the model is purposefully coming with dumb ideas or running around in circles and only when you tell it that they are trying to defraud you, they suddenly come back with a right solution.
HN’s guidelines say ‘Don’t editorialize’. The original title here is ‘[BUG] Claude Code login fails with OAuth timeout on Windows’, which is more specific and less clickbaity.
My biggest frustration right now is the seeming complete loss of background agent functionality. Permissions seem completely botched for background agents right now. When that happens, the foreground agent just takes over the task despite:
1. Me not wanting that for context management reasons
2. It burning tokens on an expensive model.
Literally a conversation that I just had:
* ME: "Have sonnet background agent do X"
* Opus: "Agent failed, I'll do it myself"
* Me: "No, have a background agent do it"
* Opus: Proceeds to do it in the foreground
* Flips keyboard
This has completely broken my workflows. I'm stuck waiting for Opus to monitor a basic task and destroy my context.
The analogy that recently came to me is like internet itself. Your advice seems to say just do everything locally on my computer without access to the internet, because internet might suffer service disruptions or price hikes in the future.
Luckily, ISPs tend to be quite reliable and don't have outrageous price hikes, but maybe that's because of regulation or focused competition, I'm not sure.
I think it's been clear from the beginning that the per-token price of usage was far below what it will be when firms have implemented their profit-maximizing price plans. "AI winter" will happen when these firms start maximizing profit. At that point it'll be too expensive for all but certain use cases to use the best technology for work.
We'll see AI chat replace Google, we'll see companies adopting AI in high-value areas, and we'll see local models like Gemma 4 get used heavily.
AI winter will see a disappearance of the clickbait headlines about everyone losing their jobs. Literally nobody is making those statements taking into account that pricing to this point is way less than the profit maximizing level.
Isn't it a little weird that we trust this app to help us build some of the most important parts of our business and the company that vends this app keep breaking it in unique ways.
At my workplace we have been sticking with older versions, and now stick to the stable release channel.
I'm more surprised that OpenAI is extremely subsidising their ChatGPT subscriptions. With Plus you can do a lot more than with Calude's x5 Max. Is it an expense they just can afford, while people have not migrated over from CC?
Just trying to win over market share I assume. OpenAI is willing to subsidize to try to get people to switch from CC to Codex, and the best incentive is to offer more tokens at a lower price.
If you prepare yourself a token with "claude setup-token" (presuming you're not already locked out and had one) you can run "CLAUDE_CODE_OAUTH_TOKEN=sk.. claude" to use your account.
If anthropic‘s reliability becomes a meme, they risk brand death like Microsoft. Go to hand it to them though, they’re really living that “AI writes all of our code and it should write your code too” life.
Is this really relevant news? Please share more bug reports from popular services and tools. Feels a tiny bit biased. My CC is just fine since at least three weeks.
I'm VERY curious about your case. What kind of switching costs do you guys have? I'm working at a very young startup that is still not locked into either AI provider harnesses -- what causes switching costs, just the subscription leftovers or something else?
FYI I use my Codex models with Claude code and they work pretty great. It can even pick up on existing conversations w/ Opus and then resume w/ OAI models.
I stopped using Claude Code several months ago and I can't say I've missed it.
There was constant drama with CC. Degradation, low reliability, harness conspiring against you, and etc – these things are not new. Its burgeoning popularity has only made it worse. Anthropic is always doing something to shoot themselves in the foot.
The harness does cool things, don't get me wrong. But it comes with a ton of papercuts that don't belong in a professional product.
Not sure how Claude and CC has become the defacto best model given gpt 5.3 codex and 5.4 exist. This space moves so fast you should be testing your workflows on different models at least once every quarter, prudently once a month.
We've got access to opus 4-6, gpt 5.4, gemini pro and a few others through corprate. I have customized agents on claude, gpt and gemini since we tend to run out of tokens for x model by the end of a month. Out of all of them I've consistently been using sonnet for most tasks. Opus functions mainly as hand-off agents and reviewer". In my anecdotal experience Claude is miles ahead of the other models and has been for a long while... when it comes to writing code the way we want it. Which eksplicit, no-abstraction, no-external packages, fail fast defensive programming. I imagine you'd get different milage with different models and different coding styles.
The rest of the organisation, which is not software development or IT related, mainly uses GPT models. I just wish I hadn't taught risk management about claude code so they weren't wasting MY tokens.
I've been an avid fan of codex for the last few month's but finally hit the weekly limit so I've wanted to try out claude code before biting the bullet and going for the 200 dollar codex sub.
Obviously in hindsight it would be unfair to Anthropic to judge them on an unstable day so I'l leave those complaints aside but I hit the session limit way too fast. I planned out 3 tasks and it couldn't finish the first plan completely, for that implementation task it has seen a grand total of 1 build log and hasn't even run any tests which already caused it to enter in the red territory of the context circle.
It was even asking me during planning which endpoints the new feature should use to hook into the existing system, codex would never ask this and just simply look these up during planning and whenever it encounters ambiguity it would either ask straight away or put it as an open question. I have to wonder if they're limiting this behavior due trying to keep the context as small as possible and preventing even earlier session limits.
Maybe codex's limits are not sustainable in the long run and I'm very spoiled by the limits but at this point CC(sonnet) and Codex(5.4) are simply not in the same league when comparing both 20 dollar subscriptions.
I will also clearly state that the value both these tools provide at these price points are absolutely worth it, it's just that codex's value/money ratio is much better.
Anthropic models haven't been far ahead for a while. Quite a few months at least. Chinese models are roughly equal at 1/6th the cost. Minimax is roughly equal to Opus. Chinese providers also haven't had the issues with uptime and variable model quality. The gap with OpenAI also isn't huge and GLM is a noticeably more compliant model (unsurprisingly given the hubristic internal culture at Anthropic around safety).
CC is a better implementation and seems to be fairly economic with token usage. That is the really the only defining point and, I suspect, Anthropic are going to have a lot of trouble staying relevant with all the product issues.
They were far ahead for a brief period in November/December which is driving the hype cycle that now appears to be collapsing the company.
You have to test at least every month, things are moving quickly. Stepfun is releasing soon and seems to have an Opus-level model with more efficient architecture.
Minimax is nowhere near Opus in my tests, though for me at least oddly 4.6 felt worse than 4.5. I haven't use Minimax extensively, but I have an API driven test suite for a product and even Sonnet 4.6 outperforms it in my testing unless something changed in the last month.
One example is I have a multi-stage distillation/knowledge extraction script for taking a Discord channel and answering questions. I have a hardcoded 5k message test set where I set up 20 questions myself based on analyzing it.
In my harness Minimax wasn't even getting half of them right, whereas Sonnet was 100%. Granted this isn't code, but my usage on pi felt about the same.
> CC is a better implementation and seems to be fairly economic with token usage. That is the really the only defining point and, I suspect, Anthropic are going to have a lot of trouble staying relevant with all the product issues.
What are you using to drive the Chinese models in order to evaluate this? OpenCode?
Some of Claude Code's features, like remote sessions, are far more important than the underlying model for my productivity.
Yes, 100% agree. OpenHands has self-hosted, KiloCode and RooCode both have a cloud option. I don't think you are able to pass a session around with any of them. Codex seems to have comparable features afaik.
CC tool usage is also significantly ahead imo (doesn't negate the price but it is something). I have seen issues with heavy thinking models (like Minimax) and client implementations with poor tool usage (like Cline).
CC has had a period over the last six months of delivering significant value...but, of course, you can just use CC with OpenRouter.
I haven't noticed a huge difference with other models but I agree that is definitely a strength (and CC has better tooling for this). However, I do think there are practical limitations to agentic workflows because of the relatively poor output vs humans. You can generate lots of code, but most of it will be shit.
Agentic workflows do have a place in well-defined, structured tasks...but I don't think that is what most people are trying to do with it.
...and codex is at least 10x better than Claude. I don't even bother starting a new session when working on a feature, a single compaction is basically unnoticeable. You have to compact several times to start needing to remind the model about a rule or two.
Unless they meant "all code that needs to be written has already been written" so their mission is to prevent any new code from being written via a kind of a bait and switch?
I found that telling Claude that it is trying to defraud you and making spend money often gets it back on track and return to pervious performance briefly until it agains starts doing nonsense.
I think Anthropics model has conflict of interest. They seem to have nerfed the models so that it takes more iterations to get the result (and spend more money) than it used to where e.g. Opus would get something right first time.
I really don't understand the way Claude does rate limiting, particularly the 5 hour limit. I can get on at 11:30, blow through my limit doing some stupid shit like processing a pile of books into my llm-wiki, and then get notified that I've used 90% of my 5 hour session limit and I have to wait for noon (aka wait 10 minutes) for the five hour limit to reset. Baffling.
I’ve been toying around at home with it and I’ve been fine with its output mostly (in a Java project ofc), but I’ve run into a few consistent problems
- The thing always trips up validating its work. It consistently tries to use powershell in a WSL environment I don’t have it installed in. It also seems to struggle with relative/absolute paths when running commands.
- Pricing makes no sense to me, but Jetbrains offering seems to have its own layer of abstraction in “credits” that just seem so opaque.
Then again, I mostly use this stuff for implementing tedious utilities/features. I’m not doing entity agent written and still do a lot of hand tweaks to code, because it’s still faster to just do it myself sometimes. Mostly all from all from the IDE still.
Maybe, but you can literally feel the difference as you type. When you type in Codex, it's fast, it feels instant. When you type in Claude Code, it feels like playing a game in 60 fps after you already got used to 144 fps.
i upgraded to the 20x plan, and hit the weekly limit within 24 hours. i was running some fairly large tasks, but was still surprised it hit the weekly session limit so quickly. now i can't use it for 6 more days :( i didn't even have time to ask it to help setup logs or something to track my usage before i hit the session limit.
How are you using it to reach the limit so quickly? I'm 13% at a 10x plan and I have used it for hours every day for the last 5 days. I never hit a limit.
I have the 20x plan and use it together with my husband. 4 days in to our weekly usage window and we're only at 54% (and we both use it the entire day)
I have no idea how people are hitting the limits so fast.
Hitting limits is more related to how many tokens it’s generating, not necessarily how complex the changes are.
Hit the weekly limit on my 20x plan last week trying to do a full front end rewrite of a giant enterprise web app, 600+ html templates, plus validating every single one with playwright.
As much as people on Hacker News complain about subscription models for productivity and creativity suites, the open arms embrace of subscription development tools (services, really) which seek to offload the very act itself makes me wonder how and why so many people are eager to dive right in. I get it. LLMs are cool technology.
Is this a symptom of the same phenomenon behind the deluge of disposable JavaScript frameworks of just ten years ago? Is it peer pressure, fear of missing out? At its root, I suspect so; of course I would imagine it's rare for the C-suite to have ever mandated the usage of a specific language or framework, and LLMs represent an unprecedented lever of power to have an even bigger shot at first mover's advantage, from a business perspective. (Yes, I am aware of how "good enough" local models have become for many.)
I don't really have anything useful nor actionable to say here regarding this dialling back of capability to deal with capacity issues. Are there any indications of shops or individual contributors with contingency plans on the table for dialling back LLM usage in kind to mitigate these unknowns? I know the calculus is such that potential (and frequently realised) gains heavily outweigh the risks of going all in, but, in the grander scheme of time and circumstance, long term commitments are starting to be more apparently risky. I am purposefully trying to avoid "begging the question" here; if instead of LLMs, this were some other tool or service, reactions to these events would have been far more pragmatic, with less of a reticence to invest time on in-house solutions when dealing with flaky vendors.
HN is a big community that has always had a mix of people who value newness as a feature vs those who prioritize simplicity and reliability. Unless you're recognizing the exact same names taking these contradictory opinions it's probably different groups of people for the most part.
It seems like every LLM thread for the past couple years is full of posts saying that the latest hot AI tool/approach has made them unbelievably more productive, followed by others saying they found that same thing underwhelming.
> I get it. LLMs are cool technology.
I don't think many of you have legitimately tried Claude Code, or maybe you're holding it wrong.
I'm getting 10x the work done. I'm operating at all layers of the stack with a speed and rapidity I've never had before.
And before anyone accuses me of being some "vibe coder", I've built five nines active-active money rails that move billions of dollars a day at 50kqps+, amongst lots of other hard hitting platform engineering work. Serious senior engineering for over a decade.
This isn't just a "cool technology". We've exited the punch card phase. And that is hard or impossible to come back from.
If you're not seeing these same successes, I legitimately think you're using it wrong.
I honestly don't like subscription services, hyperscaler concentration of power, or the fact I can't run Opus locally. But it doesn't matter - the tool exists in the shape it does, and I have to consume it in the way that it's presented. I hope for a different offering that is more democratic and open, but right now the market hasn't provided that.
It's as if you got access to fiber or broadband and were asked to go back to ISDN/dial up.
Man I really thought this was satire. It’s phenomenal that you can gain 10x benefits at all layers of the stack, you must have a very small development team or work alone.
I just don’t see how I could export 10x the work and have it properly validated by peers at this point in time. I may be able to generate code 10-20x faster, but there are nuances that only a human can reason about in my particular sector.
Senior engineer with 25 years of experience here. I wish I spent enough time actually coding that 10x-ing my coding productivity would matter much to my job. Most of my day is spent wrangling requirements, looking after junior devs, stamping out confusion brush fires before they get out of control, and generally just trying to steer the app away from a trainwreck down the line.
When I do code, it's almost always something novel that I don't know how I'm going to implement until I code a few pieces and see how they fit together. If it's a fairly routine feature based on an existing pattern, I assign it to one of the other devs.
This is basically the thing I keep coming back to with the agentic tools. It is the wrangling requirements, stamping out confusion, and steering away from a trainwreck down the line that are the actual challenging parts of the job and we can't automate those yet. Once you do actually know the code change you want to make though it is pretty nice to change it 10x faster than before.
> I just don’t see how I could export 10x the work and have it properly validated by peers at this point in time.
In my experience, the people who 10X their output with Claude Code fit one of two categories:
1. They're not really taking the time to understand the code they're submitting. They might do a skim over the output and see that it looks reasonable and passes tests, but they aren't taking time to understand the code as if they were pair programming. Only when it breaks and the LLM can't patch it up quickly do they go in and fully understand the code.
2. They moved very slowly before Claude Code. I've had some coworkers who would take 2-3 days to get a simple PR out because, to be frank, their work days weren't full of a lot of work. Every time they'd run into a question they'd stop and then bumble around for a few hours until they could talk to the ticket creator about it. They'd get tired of working on a task by 2PM and then save the rest of the work for tomorrow. They'd get an idea and decide to rewrite the PR the next day, and on and on with distractions. When they start using Claude Code the LLM doesn't have the same holdups, so now every time where they were getting stuck or tired before is replaced by an LLM powering through to some solution. Their cognitive load is reduced so they're no longer freezing up during the day. They aren't really becoming 10X engineers like they think, but really just catching up to normal pace
I don't know if we're all 10x'ing but our entire org is shipping PRs using an in-house framework akin to Stripe's Minions [1] and many of those PRs are generated from Slack. We definitely have work to do on the latter part of the SDLC to have more confidence in these changes but we can still rely on the existing observability layer to make sure things are working as expected.
Another commenter mentioned that Docker, git, etc. were all tools that greatly enhanced productivity and coding agents are just another tool that does that. I would agree, but argue that it's more impactful than all of those tools combined.
[1] https://stripe.dev/blog/minions-stripes-one-shot-end-to-end-...
Regarding point #2, while it is of course entirely possible that they are slackers it is more likely that they lack the knowledge you are leveraging in order to declare that the PRs are "simple"
I noticed that too. At start. It vaguely reminded me of the famous Navy SEAL copypasta.
What the fuck did you just fucking say about me, you little bitch?
I see some confusion from your downvotes. Sean cited the start of "navy seal copypasta"
The Navy Seal copypasta is a internet meme consisting of an absurdly over the top tough guy threat, posted to mock someone who is acting somehow aggressive, insecure, or self important online, usually after a minor argument.
Here it's full text:
>What the fuck did you just fucking say about me, you little bitch? I'll have you know I graduated top of my class in the Navy Seals, and I've been involved in numerous secret raids on Al-Quaeda, and I have over 300 confirmed kills. I am trained in gorilla warfare and I'm the top sniper in the entire US armed forces. You are nothing to me but just another target. I will wipe you the fuck out with precision the likes of which has never been seen before on this Earth, mark my fucking words. You think you can get away with saying that shit to me over the Internet? Think again, fucker. As we speak I am contacting my secret network of spies across the USA and your IP is being traced right now so you better prepare for the storm, maggot. The storm that wipes out the pathetic little thing you call your life. You're fucking dead, kid. I can be anywhere, anytime, and I can kill you in over seven hundred ways, and that's just with my bare hands. Not only am I extensively trained in unarmed combat, but I have access to the entire arsenal of the United States Marine Corps and I will use it to its full extent to wipe your miserable ass off the face of the continent, you little shit. If only you could have known what unholy retribution your little "clever" comment was about to bring down upon you, maybe you would have held your fucking tongue. But you couldn't, you didn't, and now you're paying the price, you goddamn idiot. I will shit fury all over you and you will drown in it. You're fucking dead, kiddo.
It's simpler actually: author trying to make a business developing AI product.
It is satire! They have been doing this bit for a while and people keep falling for it lol
I use Claude Code a lot, but I don't understand these "I'm doing 10X the work" comments.
I spend a lot of time reviewing any code that comes out of Claude Code. Even using Opus 4.6 with max effort there is almost always something that needs to be changed, often dramatically.
I can see how people go down the path of thinking "Wow, this code compiles and passes my tests! Ship it!" and start handing trust over to Opus, but I've already seen what this turns into 6 months down the road: Projects get mired down in so much complexity and LLM spaghetti that the codebase becomes fragile. Everyone is sidetracked restructuring messy code from the past, then fighting bugs that appear in the change.
I can believe some of the more recent studies showing LLMs can accelerate work by circa 20% (1.2X) because that's on the same order of magnitude that I and others are seeing with careful use.
When someone comes out and claims 10X more output, I simply cannot believe they're doing careful engineering work instead of just shipping the output after a cursory glance.
I find that it's relative to the amount of planning time you spend... I feel like I've gotten around 5x the output while using Claude Code w/ Opus over what I will get done myself... That said, I'm probably spending about 3x as much time planning as I would when just straight coding for/by myself. And that's generally the difference.
I can use the agent to scaffold a lot of test/demo frameworks around the pieces I'm working on pretty cleanly and have the agent fill in. I still spend a lot of time validating the tests and the code being completed though.
The errors I tend to get from the agent are roughly similar to what I might see from a developer/team that works remotely... you still need to verify. The difference is the turn around seems to be minutes over days. You're also able to observe over simply review... When I see a bad path, I can usually abort/cancel, revert back to the last commit and try again with more planning.
That's part of why I don't get AI for directly writing code at all. If I am going to be reviewing anything that comes out of it (and I will) then I might as well just write it myself. It's easier and faster, although it does also make it easier to fall victim to blind spots.
I think there’s a subset of engineers who were never all that good (we have no idea how many there are) who benefit most from llm’s.
We should also keep in mind there’s always been an insane shortage of high quality devs. So I’m not surprised with what we seeing.
But this notion that an elite dev is seeing 10x productivity gain is absolute nonsense. LLM’s hold experts back in most contexts.
You must be using it wrong, because I'm getting 100x the work done and currently at 1.5 million MRR with this SAAS I vibe coded over the weekend.
After I solved entrepreneurship I decided to retire and I now spend my days reading HN, posting on topics about AI.
You're still manually posting? All of my HN posting, trolling, shitposting and spamming is taken care of by a fleet of bots I vibecoded in the last 5 minutes.
You gest, but I know people who've done this.
"I gotta be present." Me: Reenacting the Malcolm Reynolds too many responses meme.
Mind if I use this as a copypasta for the future? This checks off every point people bring on LinkedIn and elsewhere.
In all seriousness though, writing code, or even sitting down and properly architecting things, have never been bottlenecks for me. It has either been artificial deadlines preventing me from writing proper unit tests, or the requirement for code review from people on my team who don't even work on the same codebase as I do on a daily basis. I have often stated and stand by the assertion that I develop at the speed of my own understanding, and I think that is a good virtue to carry forth that I think will stand the test of time and bring about the best organisational outcomes. It's just a matter of finding the right place that values this approach.
Edit for context: My team is an ops team that needed a couple developers; I was picked to implement some internal tooling. The deadlines I was given for the initial development are tied directly to my performance evaluation. My boss has only ever been a manager for almost two years. He has only ever had development headcount for less than a year. He has never been on a development team himself. The man does not take breaks and micromanages at every opportunity he gets. He is paranoid for his job, thinking he is going to be imminently replaced by our (cheaper) EU counterparts. His management style and verbal admonitions reflect this; he frequently projects these insecurities onto others, using unnecessarily accusatory speech. I am not the only developer on my team who has had such interactions with him. I have screenshots of conversations with him that I felt necessary to present to a therapist. This degree of time pressure is entirely unprecedented in my 20 year career. Yes, this is a dysfunctional environment.
> artificial deadlines preventing me from writing proper unit tests, or the requirement for code review from people on my team who don't even work on the same codebase as I do on a daily basis
I have never experienced this, and it sounds remarkably dysfunctional to me.
Believe me, it is very dysfunctional. As I've mentioned to your first replyer, my boss has only had developers for less than a year. This is an operations team I was assigned to in order to provide them some much needed tooling. The pressure my boss has perceived from above has led to my own significant burnout. The guy does not take days off and has always been logged into Slack on the odd hours I would need to pull up some HR form or another. I am currently off work for several months dealing with the fallout from all that.
I've tried everything I can to cope and am not sure I will be willing to return to that team once I am past my medical leave.
That’s a very junior engineer placing blame rather than looking inwards.
Beg pardon? I've been doing this for 20 years. My boss has been a boss for two years and has only had developer headcount for less than a year. This degree of pressure is unprecedented in my career.
You’ve made my point
Please explain, I'd like to have a productive dialogue about this. I assume you are referring to my boss?
It’d be cool to see your process in depth. You should record some of your sessions :)
I mostly believe you. I have seen hints of what you are talking about.
But often times I feel like I’m on the right track but I’m actually just spinning when wheels and the AI is just happily going along with it.
Or I’m getting too deep on something and I’m caught up in the loop, becoming ungrounded from the reality of the code and the specific problem.
If I notice that and am not too tired, I can reel it back in and re-ground things. Take a step back and make sure we are on reasonable path.
But I’m realizing it can be surprisingly difficult to catch that loop early sometimes. At least for me.
I’ve also done some pretty awesome shit with it that either would have never happened or taken far longer without AI — easily 5x-10x in many cases. It’s all quite fascinating.
Much to learn. This idea is forming for me that developing good “AI discipline” is incredibly important.
P.s. sometimes I also get this weird feeling of “AI exhaustion”. Where the thought of sending another prompt feels quite painful. The last week I’ve felt that a lot.
P.p.s. And then of course this doesn’t even touch on maintaining code quality over time. The “after” part when the LLM implements something. There are lots of good patterns and approaches for handling this, but it’s a distinct phase of the process with lots of complexities and nuances. And it’s oh-so-temping to skip or postpone. More so if the AI output is larger — exactly when you need it most.
I mean at this point can we just conclude that there are a group of engineers who claim to have incredible success with it and a group that claim it is unreliable and cannot be trusted to do complex tasks.
I struggle to believe that a ton of seemingly intelligent software engineers are too dumb to figure out how to use Claude code to get reliable results, it seems much more likely to me that it can do well at isolated tasks or new projects but fails when pointed at large complex code bases because it just... is a token predictor lol.
But yeah spinning up a green fields project in an extensively solved area (ledgers) is going to be something an AI shines at.
It isn't like we don't use this stuff also, I ask Cursor to do things 20x a day and it does something I don't like 50% of the time. Even things like pasting an error message it struggles with. How do I reconcile my actual daily experience with hype messages I see online?
Right, I keep seeing people talking past each other in this same way. I don't doubt folks when they say they coded up some greenfield project 10x faster with Claude, it's clearly great at many of those tasks! But then so many of them claim that their experience should translate to every developer in every scenario, to the point of saying they must be using it wrong if they aren't having the same experience.
Many software devs work in teams on large projects where LLMs have a more nuanced value. I myself mostly work on a large project inside a large organization. Spitting out lines of code is practically never a bottleneck for me. Running a suite of agents to generate out a ton of code for my coworkers to review doesn't really solve a problem that I have. I still use Claude in other ways and find it useful, but I'm certainly not 10x more productive with it.
> But yeah spinning up a green fields project in an extensively solved area (ledgers) is going to be something an AI shines at.
I couldn't disagree with this more. It's impressive at building demos, but asking it to build the foundation for a long-term project has been disastrous in my experience.
When you have an established project and you're asking it to color between the lines it can do that well (most of the time), but when you give it a blank canvas and a lot of autonomy it will likely end up generating crap code at a staggering pace. It becomes a constant fight against entropy where every mess you don't clean up immediately gets picked up as "the way things should be done" the next time.
Before someone asks, this is my experience with both Claude Code (Sonnet/Opus 4.6) and Codex (GPT 5.4).
I suspect many people here have tried it, but they expected it to one-shot any prompt, and when it didn't, it confirmed what they wanted to be true and they responded with "hah, see?" and then washed their hands of it.
So it's not that they're too stupid. There are various motivations for this: clinging on to familiarity, resistance to what feels like yet another tool, anti-AI koolaid, earnestly underwhelmed but don't understand how much better it can be, reacting to what they perceive to be incessant cheerleading, etc.
It's kind of like anti-Javascript posts on HN 10+ years ago. These people weren't too stupid to understand how you could steelman Node.js, they just weren't curious enough to ask, and maybe it turned out they hadn't even used Javascript since "DHTML" was a term except to do $(".box").toggle().
I wish there were more curiosity on HN.
So what do I do differently then?
Hypothetically, you have a simple slice out of bounds error because a function is getting an empty string so it does something like: `""[5]`.
Opus will add a bunch of length & nil checks to "fix" this, but the actual issue is the string should never be empty. The nil checks are just papering over a deeper issue, like you probably need a schema level check for minimum string length.
At that point do you just tell it like "no delete all that, the string should never be empty" and let it figure that out, or do I basically need to pseudo code "add a check for empty strings to this file on line 145", or do I just YOLO and know the issue is gone now so it is no longer my problem?
My bigger point is how does an LLM know that this seemingly small problem is indicative of some larger failure, like lets say this string is a `user.username` which means users can set their name to empty which means an entire migration is probably necessary. All the AI is going to do is smoosh the error messages and kick the can.
I have encountered the exact same kind of frustration, and no amount of prompting seems to prevent it from "randomly" happening.
`the error is on line #145 fix it with XYZ and add a check that no string should ever be blank`
It's the randomness that is frustrating, and that the fix would be quicker to manually input that drives me crazy. I fear that all the "rules" I add to claude.md is wasting my available tokens it won't have enough room to process my request.
Yup, this is why i firmly believe true productivity, as in, it aiding you to make you faster, is limited by the speed of review.
I think Claude makes me faster, but the struggle is always centered around retaining own context and reviewing code fully. Reviewing code fully to make sure it’s correct and the way I want it, retaining my own context to speed up reviews and not get lost.
I firmly believe people who are seeing massive gains are simply ignoring x% lines of code. There’s an argument to be made for that being acceptable, but it’s a risk analysis problem currently. Not one I subscribe to.
Use planning+execution rather than one-shotting, it'll let you push back on stuff like this. I recommend brainstorming everything with https://github.com/obra/superpowers, at least to start with.
Then work on making sure the LLM has all the info it needs. In this example it sounds like perhaps your hypothetical data model would need to be better typed and/or documented.
But yeah as of today it won't pick up on smells as you do, at least not without extra skills/prompting. You'll find that comforting or annoying depending on where you stand...
Always start an implementation in Claude Code plan mode. It's much more comprehensive than going straight to impl. I never read their prompt for plan mode before, but it deep-dives the code, peripheral files, callsites, documentation, existing tests, etc.
You get a better solution but also a plan file that you can review. And, also important, have another agent review. I've found that Codex is really good at reviewing plans.
I have an AGENTS.md prompt that explains that plan file review involves ranking the top findings by severity, explaining the impact, and recommending a fix to each one. And finally recommend a simpler directional pivot if one exists for the plan.
So, start the plan in Claude Code, type "Review this plan: <path>" in Codex (or another Claude Code agent), and cycle the findings back into Claude Code to refine the plan. When the plan is updated, write "Plan updated" to the reviewer agent.
You should get much better results with this capable of much better arch-level changes rather than narrow topical solutions.
If that's still not working sufficiently for you, maybe you could use more support, like a type-system and more goals in AGENTS.md?
IMO, plan mode is pretty useless. For bug fixes and small improvements, I already know where to edit (and can do it quickly with vim-fu).
For new features, I spend a bit of time thinking, and I can usually break it down in smaller tasks that are easy to code and verify. No need to wrangle with Plan mode and a big markdown file.
I can usually get things one-shotted by that point if I bother with the agent.
My manager and I have been experimenting with it for some stuff, and our most recent attempt at using plan mode was a refactor to change a data structure and make some conversion code unnecessary, then delete it. The plan looked fine, but after it ran the data structure change was incomplete, most of the conversion code was still there, and it introduced several bugs by changing lines it shouldn't have touched at all. Also removed several "why" style comments and arbitrarily changed variable names to be less clear in code it otherwise didn't change.
This was the costliest one we had access to, chosen as an experiment - took $20 over almost a half hour to run.
Did you do the plan review cycles like I suggested? It's a critical point.
Plan mode gives you a plan file, then you refine that, and impl derives from it.
Also, do you know it cost $20 because you're using the Claude API? I'd definitely use a subscription for interactive/development use.
Not the person you're replying to but yes, sometimes I do tell the agent to remove the cruft. Then I back up a few messages in the context and reword my request. Instead of just saying "fix this crash", or whatever, I say "this is crashing because the string is empty, however it shouldn't be empty, figure out why it's empty". And I might have it add some tests to ensure that whatever code is not returning/passing along empty strings.
1. I'm working in Rust, so it's a very safe and low-defect language. I suspect that has a tremendous amount to do with my successes. "nulls" (Option<T>) and "errors" (Result<T,E>) must be handled, and the AST encodes a tremendous amount about the state, flow, and how to deal with things. I do not feel as comfortable with Claude Code's TypeScript and React outputs - they do work, but it can be much more imprecise. And I only trust it with greenfield Python, editing existing Python code has been sloppy. The Rust experience is downright magical.
2. I architecturally describe every change I want made. I don't leave it up to the LLM to guess. My prompts might be overkill, but they result in 70-80ish% correctness in one shot. (I haven't measured this, and I'm actually curious.) I'll paste in file paths, method names, struct definitions and ask Claude for concrete changes. I'll expand "plumb foo field through the query and API layers" into as much detail as necessary. My prompts can be several paragraphs in length.
3. I don't attempt an entire change set or PR with a single prompt. I work iteratively as I would naturally work, just at a higher level and with greater and broader scope. You get a sense of what granularity and scope Claude can be effective at after a while.
You can't one shot stuff. You have to work iteratively. A single PR might be multiple round trips of incremental change. It's like being a "film director" or "pair programmer" writing code. I have exacting specifications and directions.
The power is in how fast these changes can be made and how closely they map to your expectations. And also in how little it drains your energy and focus.
This also gives me a chance to code review at every change, which means by the time I review the final PR, I've read the change set multiple times.
I hope you're not 100% serious.
Otherwise you should switch to haskal since it makes logic errors and bugs mathematically impossible.
“I struggle to believe that a ton of seemingly intelligent software engineers are too dumb to figure out how to use Claude code to get reliable results”
Seemingly is doing the heavy lifting here. If you read enough comment threads on HN, it will become obvious why they aren’t getting results.
> I struggle to believe that a ton of seemingly intelligent software engineers are too dumb to figure out how to use Claude code to get reliable results.
They're not dumb, but I'm not surprised they're struggling.
A developer's mindset has to change when adding AI into the mix, and many developers either can’t or won’t do that. Developers whose commits that look something like "Fixed some bugs" probably aren’t going to take the time to write a decent prompt either.
Whenever there's a technology shift, there are always people who can't or won't adapt. And let's be honest, there are folks whose agenda (consciously or not) is to keep the status quo and "prove" that AI is a bad thing.
No wonder we're seeing wildly different stories about the effectiveness of coding agents.
Here's my 100 file custom scaffolding AI prompt that I've been working on for the last four months, and can reliably one-shot most math olympic problems and even a rust to do list.
Case in point
Let's come back to these comments in ten years, shall we? Should be pretty entertaining.
I see two basic cases for the people who are claiming it is useless at this point.
One is that they tried AI-based coding a year or two ago, came to the IMHO completely correct at that time conclusion that it was nearly useless, and have not tried it since then to see that the situation has changed. To which the solution is, try it again. It changed a lot.
The other are those who have incorporated into their personal identity that they hate AI and will never use it. I have seen people do things like fire AI at a task they have good reasons to believe it will fail at, and when it does, project that out to all tasks without letting themselves consciously realize that picking a bad task on purpose skews the deck.
To those people my solution is to encourage them to hold on to their skepticism. I try to hold on to it as well despite the incredible cognitive temptation not to. It is very useful. But at the same time... yeah, there was a step change in the past year or so. It has gotten a lot more useful...
... but a lot of that utility is in ways that don't obviate skilled senior coding skills. It likes to write scripting code without strong types. Since the last time I wrote that, I have in fact used it in a situation where there were enough strong types that it spontaneously originated some, but it still tends to write scripting code out of that context no matter what language it is working in. It is good at very straight-line solutions to code but I rarely see it suggest using databases, or event sourcing, or a message bus, or any of a lot of other things... it has a lot of Not Invented Here syndrome where it instead bashes out some minimal solution that passes the unit tests with flying colors but can't be deployed at scale. No matter how much documentation a project has it often ends up duplicating code just because the context window is only so large and it doesn't necessarily know where the duplicated code might be. There's all sorts of ways it still needs help to produce good output.
I also wonder how many people are failing to prompt it enough. Some of my prompts are basically "take this and do that and write a function to log the error", but a lot of my prompts are a screen or two of relevant context of the project, what it is we are trying to do, why the obvious solution doesn't work, here's some other code to look at, here's the relevant bugs and some Wiki documentation on the planning of the project, we should use {event sourcing/immutable trees/stored procedures/whatever}, interact with me for questions before starting anything. This is not a complete explanation of what they are doing anymore, but there's still a lot of ways in which what an LLM can really do is style transfer... it is just taking "take this and do that and write a function to log the error" and style-transforming that into source code. If you want it to do something interesting it really helps to give it enough information in the first place for the "style transfer" to get a hold of and do something with. Don't feel silly "explaining it to a computer", you're giving the function enough data to operate on.
I can see huge utility with AI as a guide and helper.
But not being one leg in the code myself is not something I am comfortable with. It starts feeling like management and not development. I really feel the abdication very strongly and it makes me unable and unwilling to put a hard stamp on quality. I have seen too much hallucination or half missed requirements to put that much trust in AI.
It's the same with code reviews of hard tickets. You can scroll past and just approve, but do you really understand what your colleague has built? Are you really in the driver's seat? It feels to me like YOLOing with major consequences.
I dont but, at all that people doing 20x output have any idea what they are coding. They are just pressing the yolo button and no one, not the engineer, not the AI and not management is in the driver's seat. it is a very scary time.
I'm still reviewing all the code that's created, and asking for modifications, and basically using LLMs as a 2000 wpm typist, and seeing similar productivity gains. Especially in new frameworks! Everything is test driven development, super clean and super fast.
The challenge now is how to plan architectures and codebases to get really big and really scale, without AI slop creating hidden tech debt.
Foundations of the code must be very solid, and the architecture from the start has to be right. But even redoing the architecture becomes so much faster now...
I'm getting 1,000x improvement building notepad applications with 6 9s. No one is faster.
Need some help selling these notepad apps, do you have a prompt for that?
I don't want to sound like I'm trying to one-up you, but I've basically vibe coded the entire internet.
I'm surprised nobody thought of it before me but basically the LLM's are trained on the internet and I just had it spit back out everything.
It's running in parallel so I can validate it, which of course I'm using LLM's to do that.
Once it's ready I will put it on the market, but get this, my internet will be cheaper than the current internet. I'll probably just make it one cheaper, like if the current internet costs, for example, 7, I'll make my internet cost 6.
> and I have to consume it in the way that it's presented
I'm just curious, why do you "have to"? Don't get me wrong, I'm making the same choice myself too, realizing a bunch of global drawbacks because of my local/personal preference, but I won't claim I have to, it's a choice I'm making because I'm lazy.
What are the reasonable options besides a Claude Code subscription (or an equivalent from Codex or Copilot)?
I could pay API prices for the same models, but aside from paying much more for the same result that doesn't seem helpful
I could pay a 4-5 figure sum for hardware to run a far inferior open model
I could pay a six figure sum for hardware to run an open model that's only a couple months behind in capability (or a 4-5 figure sum to run the same model at a snail's pace)
I could pay API costs to semi-trustworthy inference provider to run one of those open models
None of those seem like great alternatives. If I want cutting-edge coding performance then a subscription is the most reasonable option
Note that this applies mostly to coding. For many other tasks local models or paid inference on open models is very reasonable. But for coding that last bit of performance matters
I use my OAI subscription on my Claude Code. I get the benefit of the Claude Code interface with the intelligence of OAI models.
https://prabal.ca/posts/claude-code-chatgpt-subscription/
My job title is "provide value".
I'm given a tool that lets me 10x "provide value".
My personal preferences and tastes literally do not matter.
As a professional you have a choice in how you produce whatever it is you produce. Sure, you can go for the simplest, most expensive and "easiest" way of doing things, or you can do other things, depending on your perspective and requirements. None of this is set in stone, some people make choices based on personal preferences, and that matters as much to them as your choices matter to you.
> fact I can't run Opus locally
Yet
> If you're not seeing these same successes, I legitimately think you're using it wrong.
What is “using it right”? You wrote claims, but explain nothing about your process. Anything not reproducible is either luck or lie.
> And before anyone accuses me of being some "vibe coder", I've built five nines active-active money rails that move billions of dollars a day at 50kqps+, amongst lots of other hard hitting platform engineering work. Serious senior engineering for over a decade
You sound like a pro wrestler. I'd like to know what "hard-hitting" engineering work is. Hydraulic hammers?
I mean five nines is legitimately difficult to accomplish for a lot of problem spaces.
It's also like.... difficult to honestly and accurately measure. And account for whether or not you're getting lucky based on your underlying dependencies (servers, etc) not crashing as much as advertised, or if it's actually five nines. Or whether you've run it for a month and gotten <30s of measure downtime and declared victory, vs run it for three years with copious software updates.
I always assume most people claiming five nines are just not measuring it correctly, or have not exercised the full set of things that will go wrong over a long enough period of time (dc failures, network partitions, config errors, bad network switches that drop only UDP traffic on certain ports, erroneous ACL changes, bad software updates, etc etc)
Maybe they did it all correct though, in which case, yea, seems hard hitting to me.
5 nines is at best a temporary achievement, given enough time.
I read this as satire. I still think it is.
> the open arms embrace of subscription development tools (services, really) which seek to offload the very act itself makes me wonder how and why so many people are eager to dive right in
Here's a reason not in your list.
Short version: A kind of peer pressure, but from above. In some circles I'm told a developer must have AI skills on their resume now, and those probably need to be with well known subscription services, or they substantially reduce their employment prospects.
Multiple people I know who are employers have recently, without prompting, told me they no longer hire developers who don't use AI in their workflow.
One of them told me all the employers they know think "seniors" fall into two camps, those who are embracing AI and therefore nimble and adaptive, and those who are avoiding it and therefore too backward-looking, stuck-in-their-ways to be a good hire for the future. So if they don't see signs of AI usage on a senior dev's resume now, that's an automatic discard. For devs I know laid off from an R&D company where AI was not permitted for development (for IP/confidentiality reasons), that's unfair as they were certainly not backward-looking people, but the market is not fair.
Another "business leader" employer I met recently told me his devs are divided into those who are embracing AI and those who aren't, said he finds software feature development "so slow!", and said if it wasn't for employment law he'd fire all his devs who aren't choosing to use AI. I assume he was joking, but it was interesting to hear it said out loud without prompting.
I've been to several business leadership type meetups in recent months, and it seems to be simply assumed that everyone is using AI for almost everything worth talking about. I don't think they really are, so it's interesting to watch that narrative playing out.
Apart from local AI, a serious choice is aggregated API such as new-api [0]. An API provider aggregated thousands of accounts has much better stability than a single account. It's also cheaper than the official API because of how the subscription model works, see e.g. the analysis [1].
[0] https://github.com/QuantumNous/new-api
[1] https://she-llac.com/claude-limits
>An API provider aggregated thousands of accounts has much better stability than a single account
Isn't this almost certainly against ToS, at least if you're using "plans" (as opposed to paying per-token)?
You don't even need to be a customer served by Anthropic or OpenAI so the Terms of Service are irrelevant. That's how I live in China and use almost free Claude and GPT which they don't sell here.
Wait, is this just something like openrouter, that routes your requests to different API providers, where you're paying per-token rates? Or is this taking advantage of fixed price plans, by offering an API interface for them, even though they're only supposed to be used with the official tools?
It's taking advantage of fixed price plans or even free plans.
considering it has things like a turnstile "handler", I'm assuming it attempts to abuse the free chat interface.
That seems like Anthropic's problem.
It's going to be quickly your problem when they figure out you're breaching ToS and ban your account.
The whole point of these services is that it’s not your account. It’s very much anthropic’s problem, and honestly I don’t care they’re getting ripped off.
So... I make another account? Problem solved.
I think some workflows are just that much faster with AI. And if not I can spare the time for a prompt to get work done in parallel to the stuff I work on.
There is a cost though, the context switches of topics aren't free. But if I need to visualise a something, I let an LLM create a page. If I have two tables of data that needs to be joined/mapped, I let an LLM do the first shot, often that is enough.
I cannot even hope to reach that speed. It isn't a magic tool, but it really accelerates some task.
That speed allows for in-house solutions to become viable again, software that really adapts specific business processes instead of some wonky ERP package that never really fit what you were trying to do.
I have our dbs schema checked into a Gitea repository, which our AIs can just access to quickly ingest schema definitions. If data safety is an issue, use a local model. It is extremely beneficial if you quickly can establish context and let your AI deal with real problems. And it is quite good at that.
I really enjoy coding. I've build a number of projects, personal and professional, with Python, Rust, Java and even some Scala in the mix. However, I've been addicted to Claude Code recently, especially with the superpowers skill. It feels like I can manifest code with my mind. When developing with Claude, I am presented with design dilemmas, architectural alternatives, clarification questions, things that really make me think about the problem. I then choose a solution, propose alternatives, discuss, and the code manifests. I came to realize that I enjoy the problem solving, not the actual act of writing the code. Like I have almost cloned my self, and my clones are working on the projects and coming back to me for instructions. It feels amazing
"Addicted" "Superpowers" "manifest with my mind" "it feels amazing"
Why does it sound like you're on drugs? I know that sounds extremely rude, but I can't think of any other reasonable comparison for that language.
It's hard to take these kinds of endorsements seriously when they're written so hyperbolically, in terms of the same cliches, and focused on entirely on how it makes you feel rather than what it does.
Reading a bunch of posts related to Claude Code and some folks voice genuine upset about rate limits and model intelligence while others seem very upset they can't get their fix because they've reached the five hours limits is genuinely concerning to how addictive LLMs can be for some folks.
I think the social aspect is underreported. I think this applies even for people using Claude Code and not just those treating an LLM as a therapist. In other words, I wonder how many of these people can't call their doctor to make an appointment or call a restaurant to order a pizza. And I say this as someone who struggles to do those things.
People claim that DoorDash and other similar apps are about efficiency, but I suspect a large portion is also a desire to remove human interaction. LLMs are the same. Or, in actuality, to create a simulacrum of human interaction that is satisfying enough.
It's reflecting the value we get from it, relative to the cost of continuing if we switch to the API pricing. It is genuinely upsetting to hit the limits when you face a substantial drop in productivity.
Imagine being an Uber driver and suddenly have to switch to a rickshaw for several hours.
"superpowers" is the exact name of the specific Claude code skill. The rest of your concerns is just me expressing my excitement, as until recently I was very skeptic of the whole vibe-coding movement, but have since done a complete 180.
The drug is the llm coding. I kind of get it, when I was a kid and first got a computer I felt the same way after I learned assembly language. The world is your oyster and you can do what felt like anything. It was why I spent almost every waking hour working on my computer. That wore off eventually but I've spent some time on my backlog of projects with Claude and it feels bit like the old days again.
> Why does it sound like you're on drugs, specifically cocaine?
This has basically been what all of Silicon Valley sounds like to me for a few years now.
They are known for abusing many psycho-stimulants out there. The stupid “manifesto” Marc Andreessen put out a while back sounded like adderall-produced drivel more than a coherent political manifesto.
If I were to go off into the woods, take a lot of drugs, and write my own crank manifesto, the central conceit would be that ADHD is the key to understanding the entirety of Silicon Valley. A bunch of people with stimulus driven brains creating technologies that feed themselves and the rest of the populace more and more stimulation, setting a new baseline and requiring new technologies for higher levels of stimulation in an endless loop until we all stimulate ourselves to death. Delayed gratification is the enemy.
This is similar to how we have already found hacks in our evolutionary programming to directly deliver high amounts of flavor without nutrition, and we've been working on ever more complex means of delivering social stimulation without the need for other human (one of the key appeals of AI for many people, as well).
Of course these are all the ravings of a crank and should be ignored.
No, you're right. But a million monkeys on cocaine may eventually provide value to shareholders.
I feel this sentiment. It’s more like pair programming with someone both smarter and dumber than you. If you’re reviewing the code it is putting down, you’re likely to spot what it’s getting wrong and discussing it.
What I don’t understand, are the people who let it go over night or with whole “agent teams” working on software. I have no idea how they trust any of it.
Yep, I want to make stuff. Writing the code by hand was just a means to an end.
That’s like saying enjoying composing music, but not enjoying playing music. Or creating stories, but don’t like writing. Yes they’re different activities, but linked together. The former is creativity, the latter is a medium of transmission.
Code is notation, just like music sheets, or food recipes. If your interaction with anyone else is with the end result only (the software), the. The code does not matter. But for collaboration, it does. When it’s badly written, that just increase everyone burden.
It’s like forcing everyone to learn a symphony with the record instead of the sheets. And often a badly recorded version.
> That’s like saying enjoying composing music, but not enjoying playing music
Do you think that is impossible? There are plenty of people who enjoy composing music on things like trackers, with no intent of ever playing said music on an instrument.
I love coding, but I also like making things, and the two are in conflict: When I write code for the sake of writing code, I am meticulous and look for perfection. When I make things, I want to move as fast as possible, because it is the end-product that matters.
There is also a hidden presumption in what you've written that 1) the code will be badly written. Sometimes it is, but that is the case for people to, but often it is better than what I would produce (say, when needing to produce something in a language I'm not familiar enough with), 2) and that the collaboration will be with people manually working on the code. That is increasingly often not true.
> When I write code for the sake of writing code,
I struggle to understand that comparison. Code is notation, you can’t write code for the sake of writing code. You have a problem and you instruct the computer how to do it. And for the sake of your collaborator and your futher self, you take care of how you write that. There’s no real distinction IMO.
> There is also a hidden presumption in what you've written that 1) the code will be badly written
The computers does not really care about what programming language you’re using and the name of your variables and other indentifiers. People do. You can have correct code (decompiled assembly or minified JavaScript) and no one will wants to collaborate on that.
Code is often the most precise explanation of some process. By being formal, it’s a truthful representation of the process. Specs and documentations can describe truth, but they do not embody it.
You can always collaborate with markdown files. But eventually someone will have to look at the code and understand what it does, because that’s the truth that matters. Anything else is prayers and hope. And if you’ve never cared about maintainability and quality of the code, it will probably be an arduous process.
> Code is notation, you can’t write code for the sake of writing code.
Of course you can.
> You have a problem and you instruct the computer how to do it.
And sometimes that problem is not the point. Just like sometimes I write for the joy of writing, not because I particularly care about a reader or the meaning of the output.
> The computers does not really care about what programming language you’re using and the name of your variables and other indentifiers. People do. You can have correct code (decompiled assembly or minified JavaScript) and no one will wants to collaborate on that.
This has no relation whatsoever to the sentence you quoted.
> This has no relation whatsoever to the sentence you quoted.
Maybe I wasn’t clear. What I wanted to convey is that the use of programming languages, paradigms, patterns, and other software engineering principles is related to the human side of programming.
You can solve a problem correctly, but with the resulting code being hard to parse. Or you can write readable code but with bugs. And almost everyone prefers the latter.
So badly written means incomprehensible code, mostly due to the size of it in the case of Agents. It’s all right if no one cares about the code. But if you expect someone to review it, changeset that even the author don’t understand is slop.
So again, this presumes that the result must be incomprehensible. That is not at all my experience. It may become incomprehensible if you let it, just as is the case with human developers. It won't be if you enforce reviews, and your harness demands cleanups and sets clear standards.
Using your analogy, I enjoy composing music and enjoy playing music. I don't enjoy going through the notion of writing the notes on a piece of paper with the pen. I have to do it because people can't read my mind, but if they could I would avoid it. Claude code is like that. The code that gets written, feels like the code that I would have written
> if instead of LLMs, this were some other tool or service, reactions to these events would have been far more pragmatic, with less of a reticence to invest time on in-house solutions when dealing with flaky vendors
As an example, a long term goal at the employer I work for is exactly this: run LLMs locally. There's a big infrastructure backlog through, so it's waiting on those things, and hopefully we'll see good local models by then that can do what Claude Sonnet or GPT-5.3-Codex can do today.
Well, I wanted to understand what is this cool new tech everybody is talking about so I bought a Max plan, experimented with various setups recommended by various experts, vibe-coded a few apps and then threw it all away.
I still use more traditional approach for finding bugs and other issues in my code, but the agentic workflow doesn't give me any net value.
People will always go along with a removal of friction even against their benefit. It's natural bias, we have a preference for not spending energy.
It's why we pay stupid amounts for takeout when it's a button away, it's why we accept the issues that come with online dating rather than breaking the ice outside, it's why there's been decades scams that claim to get you abs without effort...
LLMs are the ultimate friction removal. They can remove gaps or mechanical work that regular programming can, but more importantly they can think for you.
I'm convinced this human pattern is as dangerous as addiction. But it's so much harder to fight against, because who's going to be in favor of doing things with more effort rather than less? The whole point of capitalism is supposed to be that it rewards efficiency.
> stupid amounts for takeout
Aw hell. You found my vice and my own cognitive dissonance here. If I want to truly stand by my convictions, I should probably cook more and log off. Waiting for signs that the tides are turning and that people are beginning to value a slower, more methodical approach again isn't doing anything in the current moment to stave off the genuine feelings of dread that have honestly led to some suicidal ideation.
(this is serious and not sarcasm, by the way)
Think that you're likely average!
By which I mean, it's likely you're not the only one feeling that dread. We're due for a counter movement, and it's a matter of time to see it flower.
Stand strong. Plenty of us working towards healthy offline communities.
Thanks friend. I really appreciate that. This is genuinely hard right now.
Think of the stupidest product you can think of and you likely only know about it because people buy/bought them en masse. AI is no different from any other product; plenty will pay/adopt for exactly the reasons you said. There is powerful motivations for people to feel “ahead” of others (or more informed, or more “cool”, or more knowledgeable, or more experienced, or whatever their ego requires), even if their situation is exactly the same.
That said, I’m not sure I follow your statement of less resistance to the development of internal tools when the opposite seems to be the case; companies (or more specifically developers) are perhaps too quick to think they can just vibe-code a replacement for any vendor in a weekend these days.
Contingency plan? Just code without it like before. AI could disappear today and I would be very disappointed but it's not like I forgot how to code without it. If anything, I think it's made me a better programmer by taking friction away from the execution phase and giving me more mental space to think in the abstract at times, and that benefit has certainly carried over to my work where we still don't have copilot approved yet.
I would love nothing more than ditching Claude for a local solution tomorrow. But it doesn't exist today, so it is what it is - you gotta keep up with the joneses.
Maybe in 5 years we'll have an open weights model that is in the "good enough" category that I can run on a RTX 9000 for 15k dollars or whatever.
I don't want to get too much into the details but I don't work in or for the Valley and I don't think I'll ever be able to afford that sort of expenditure on computing. A down payment on a car, or a vital medical procedure? Sure. I'm probably not alone here.
>I get it. LLMs are cool technology.
It would be cool to run SOTA models on my own hardware but I can't. Hence, the subscription.
I think most people understand the need for subscriptions here. It is an ongoing massive compute cost, and that’s what you’re paying for. Your local system is not capable of running the massive amount of compute required for this. If it were then we would see more people up in arms about it.
We could run it locally, but the problems that matter simply don't change.
We're paying for servers that sit idle at night, you don't find enough sysadmins for the current problems, the open source models aren't as strong as closed source, providing context (as in googling) means you hook everything up to the internet anyway, where do you find the power and the cooling systems and the space, what do you do with the GPUs after 3 years?
Suddenly that $500/month/user seems like a steal.
Is this pace necessary? I feel like this is causing people to consider code to be disposable, and I think that both are a massive mistake.
The great part is that you can always build your own selfhosted tools. There is nothing that can't be done at home, it's just a calculation of how much you're willing to spend.
Lately though the RAM crisis is continuing and making things like this more unfeasible. But you can still use a lot of smaller models for coding and testing tasks.
Planning tasks I'd use a cloud hosted one, for now, because gemma4 isn't there yet and because the GPU prices are still quite insane.
The cool and fun part is that with ollama and vllm you can just build your own agentic environment IDE, give it the tools you like, and make the workflow however you like. And it isn't even that hard to do, it just needs a lot of tweaking and prompt fiddling.
And on top of that: Use kiwix to selfhost Wikipedia, stackoverflow and devdocs. Give the LLM a tool to use the search and read the pages, and your productivity is skyrocketing pretty quickly. No need anymore to have internet, and a cheap Intel NUC is good enough for self-hosting a lot of containers already.
Source: I am building my own offline agentic environment for Golang [1] which is pretty experimental but sometimes it's also working.
[1] https://github.com/cookiengineer/exocomp
I'm definitely all in on self-hosting, though I rent my compute and pay for bandwidth with Linode and storage with rsync.net.
The LLM bit though, personally, is just not for me.
Mounting evidence that claude max users are put into one big compute fuel pool. Demand increased dramatically with OpenAI's DoD PR snafu (even though Anth was already working with the DoD? But I digress...). The pool hit a ceiling. Anth has no compute left to give. Hence people maxing out after 1 query. "Working on it" means finding a way to distill Claude Code that isn't enough of a quality degradation to be noticed[0], in order to get the compute pool operational again. The distillation will continue until uptime improves.
0 as of this writing, it's noticeable. Lots of "should I continue?" And "you should run this command if you want to see that information." Roadblocks that I hadn't seen in a year+
There's another piece of the puzzle. Dario has very clearly stated they are not taking the OpenAI approach of spending $trillion to scale right now and assume the money comes later. They are spending significantly less and working towards profitability sooner.
That means they are going to be far more constrained infrastructurally than some of the competition. I think this is some of the constraints that we are seeing.
He did say that. And, in virtually the same breath, said they would have to spend $trillions if they hope to remain SOTA, which they have to be [0],[1].
They don't have compute because they didn't play the game and get the good rates a couple of years ago, and are now forced to work with third-rate providers. That's not a strategy.
I would take everything he says with a huge grain of salt.
[0] “We’re buying a lot. We’re buying a hell of a lot. We’re buying an amount that’s comparable to what the biggest players in the game are buying.”
“Profitability is this kind of weird thing in this field. I don’t think in this field profitability is actually a measure of spending down versus investing in the business.”
[1] “You don’t just serve the current models and never train another model, because then you don’t have any demand because you’ll fall behind.”
So he's not spending so they can be profitable, AND spending as much as the biggest players are spending, AND not really looking at profit as a measure of anything? K.
no grand strategy behind that
they're looking to IPO in 2028 vs 2030 for OpenAI, who have raised more than double the funds
so they're willing to play fast and loose with the terms and conditions of existing customers trying to make it happen
those pockets must be drying up really fast
Alternatively, the elephant in the room I'm surprised no one wants to talk about: the vibe coding is catching up with them.
I don't think anyone is talking about it because it's not a very productive conversation to have. I'm not particularly bullish on vibe coding either but if you could explain what exactly about vibe coding causes these specific issues then it could be more interesting to discuss.
But as it stands, the more likely reason is capacity crunch caused by a chips shortage and demand heavily outpacing supply. You vibe coding reason is based on as much vibes as their code probably is.
Vibe coding does not usually produce performant code, it produces spaghetti with the goal of making the user asking for work to be done to go away as soon as possible with a (often barely) working solution.
I recently vibe-translated a simple project from Javascript to C, where Javascript was producing 30fps, and the first C version produced 1 frame every 20 seconds. After some time trying to get the AI to optimize it, I arrived at 1fps from the C project. Not a win, but the AI did produce working C code.
I have no doubt that if I had done this myself (which I will do soon), with the appropriate level of care, it would have been 30fps or more.
that is a separate issue indeed, but their comms make it rather obvious they are scrambling to reduce compute and they're just slashing their service selectively - with openclaw and max users being the first in the chopping block
If an AI doesnt generate perfect code, if left to its devices it will at some point create a codebase big and nasty enough that it will not be able to deal with it.
It should catch up faster. It's absolutely useless for the bulk of the tedium—notably, soldering together random repos to satisfy executives—that makes up my job now.
That's mostly been my job since I started around 2010 haha
That's not an elephant in the room.. it's just proof of how insanely useful the tool is and the reality that so much more hardware is needed. Thus people saying "why are these companies building insanely large data centers" ... this is why!
The problem is that vibe-coding, when it fails (i.e. it's non-useful, at least for a bit), is usually solved by more vibes. Try again and hope it works. Ask it to refactor and hope the cleaner code helps it along. If you're willing to think about the code yourself you'll likely ask it questions about the codebase. High vibe-code usage is both a metric that it is working and that it's failing.
I think it is telling that this audience down votes this. It's kind of obvious that the thing is being used a lot. Doesn't mean it works as well as advertised. Doesn't mean the business model they have works. Just means there is a lot of demand. You can't ignore that.
That is only true if there's a pricepoint that vibecoders are willing to pay per token that allows Anthropic to make a profit.
I have no particular insight into the Anthropic backend, but it's possible in general for systems to have architectural issues which cannot be mitigated by just adding more hardware.
maybe you should study up on correlation and causation before you declare "proof"; it's also possible that it goes the other way.
The proof is already there. It's concrete. I've seen it directly the last few months of using claude code. It closed the loop. It's insanely beneficial when used properly- that is a pure fact. You act like it's an opinion.
I was vacationing! What's up with OpenAI now? Asking with some morbid curiosity tbh.
I believe the first part is referring to these:
https://news.ycombinator.com/item?id=47186677
https://news.ycombinator.com/item?id=47199948
Nothing, Effective Altruist dweebs realizing that the world isn't their psychology experiment.
As a person that hasn’t used Claude code before, I’ve been using OpenAI’s Codex and it is pretty amazing. I wonder how much more amazing Claude is.
Both are great, where they differ is: Claude Code has a better instinct than Codex. Meaning it will naturally produce things like you, the developer, would have.
Codex shines really well at what I call "hard problems." You set thinking high, and you just let it throw raw power at the problem. Whereas, Claude Code is better at your average day-to-day "write me code" tasks.
So the difference is kind of nuanced. You kind of need to use both a while to get a real sense of it.
I think the way I and others use it is code with clause, review or bug hunt with codex. Then I pass the review back to Claude for implementation. Works well. Better than codex implementation and finds gaps versus using Claude to review itself in my opinion.
Codex switched to paid API tokens only. Not to mention their alignment with the department of war.
> Codex switched to paid API tokens only.
They’re still doing subscriptions: https://developers.openai.com/codex/pricing
I'm happy I invested in setting up Codex CLI and getting it to work with ollama. For the toughest jobs I can use Github Copilot (free as an academic) or Gemini CLI. If we see the per token price increase 5x or 10x as these companies move to focusing on revenue, local models will be the way to go, so long as stuff like Gemma 4 keeps getting released.
That's not true.
There was a headline saying they were, and the actual article showed they were doing nothingbof the sort.
If you read HN headlines, and don't even bother to click into the comments and see everyone calling out the headline as bogus, you might think something like your statement is true.
Can you give context for the API thing?
Edit: Looks like it still works with subs, they just measure usage per token instead of per message.
Codex just changed the way they calculate usage with a massive negative impact.
Before a Subscription was the cheapest way to gain Codex usage, but now they've essentially having API and Subscription pricing match (e.g. $200 sub = $200 in API Codex usage).
The only value of a subscription now is that you get the web version of ChatGPT "free." In terms of raw Codex usage, you could just as easily buy API usage.
edit: This is currently rolled out for Enterprise, but is coming to Pro/Plus soon. The people below saying "I haven't had this issue" haven't yet*.
> e.g. $200 sub = $200 in API Codex usage [...] In terms of raw Codex usage, you could just as easily buy API usage.
I don't think it's made out like that, I'm on the ChatGPT Pro plan for personal usage, and for a client I'm using the OpenAI API, both almost only using GPT 5.4 xhigh, done pretty much 50/50 work on client/personal projects, and clients API usage is up to 400 USD right now after a week of work, and ChatGPT Pro limit has 61% left, resets tomorrow.
Still seems to me you'd get a heck more out of the subscription than API credits.
This. ChatGPT Pro personal at $20/month and using GPT 5.4 xhigh is the best deal currently. I don't know if they are actually losing money or betting on people staying well under limits. Clearly they charge extra to businesses on the API plans to make up for it.
In the future, open models and cheaper inference could cover the loss-leading strategies we see today.
ChatGPT Personal Pro plan hasnt had the change yet. It is rolling out to Enterprise users first.
Right, because you're on the old and not new structure.
They just rolled it out for new subscribers and existing ones will be getting it in the "coming weeks." Enterprise already got hit with this from my understanding.
This is not true. The change applies to the credits, ie the incremental usage that exceeds your subscription limits.
OpenAI's own help page suggests otherwise.
I looked at my cc usage and I was at 90% of my weekly allowance after 3 days of use...BUT, if I looked at the usage stats with the chart, it showed, on a scale of 1-4 intensity of usage (4 being most intense), the three days as such:
Day 1: 2
Day 2: 3
Day 3: 1
Not sure how I can hit such limits so quickly with such low scores on its own chart.
The limits are smaller now, is how.
Then why not update their chart to at least say that? The numbers (shading, actually) on the chart are not absolute numbers, they're relative, so just make it look as if I spent a lot of time on it. If they're gonna change their limits without being clear about it, at least go all the way. Right now, I can go, "See, you're actually saying I didn't use that much compared to the limits."
Which is fine, but the way they're tightening the screws, and not saying until they announce the results of their A/B tests is very frustrating.
I agree; I think that's what happened. But it's a shame—I'm having a lot of trouble with poor-quality results from Claude-Code, and the session limit is being used up quickly.
Makes sense, even plan name seems to agree: "Claude Max".
Reminds me of an “all you can eat” buffet I was at once where the owner told me, “that’s it, that’s all you can eat” and cut it off.
Did this prompt some reflection on your part?
What, that businesses lie?
It’s like most lifetime warranties. They’re not what they seem to mean colloquially. They have a contractual meaning.
Or my grocery store that has certain products with signs "Always $n" but over the past 5+ years n has increased regularly and dramatically.
They never said WHOSE lifetime...
I think with some it’s the lifetime of the product line. If it’s sunset, no longer sold; lifetime ends when support ends.
That we accept the lying doesn't mean it's good.
Sounds like the most blatant case of false advertising since the movie The Neverending Story
What is openai's involvement here, as I am out of the loop.
Claude: Autonomous weapons and domestic surveillance are our red line
Pentagon: No
OpenAI: We are okay if the line is merely a suggestion and we encourage you not to cross it!
Pentagon: Yes we pick that option
I assume it's anthropic rejecting the US Government's use of their software for domestic mass surveillance or fully autonomous weapons, and openai happily agreeing to it.
That has led to a significant number of people switching over from openai, or at least stating they were going to do so.
They made a $25 million donation to Trump, which was repaid in kind by designating Anthropic a supply chain risk. Unfortunately, they weren’t nearly subtle enough about this, and went “sure, we’ll take over the contract with no limits on killbots or domestic surveillance, no problem!” on the same day as Anthropic got in trouble, and people put two and two together.
On the nose. Dealt with this last week. Ran maybe 5 queries (not even in code) and was maxed out for the day. What a great way to spend my money
Distillation is how they're planning to make money? What a poor strategy. This is next level FOMO (Fear Of Not Being The #1 LLM Provider).
I have cancelled my subscription last week, I'll see them when they fix this nonesense
The responsible thing would be to not sell way more subscriptions than their capacity. But they have to show the exponential revenue curves to their investors. I cancelled my subscription yesterday.
The trend on the status page[1] does not inspire confidence. Beginning to wonder if this might be a daily thing.
[1] https://status.claude.com/
They went from $9b ARR at the end of 2025 to $30b ARR today. That's more than 3x the size in 3 months. I expect growing pains.
For some context, they added 2x Palantir or .75x Shopify or .68x Adobe annual revenue in March alone.
Yeah its huge demand upswing from the growth of openclaw and similar pushing resources. Very clear from recent changes and announcement around this [0]
Fwiw there are worse delays from second tier providers like moonshot's kimik2.5 that are also popular for agentic use.
[0] https://news.ycombinator.com/item?id=47633396
It's also worth keeping in mind that Anthropic's compute needs are nothing like those of a company like Shopify or Adobe, so revenue might not paint accurately enough the picture of what they're dealing with right now.
And they are early adopters of the vibe coding paradigm, having a 100% Claude generated codebase.
I assume most of their outages is related to this insane scaling and lack of available compute.
Vibe coding doesn't automatically mean lower quality. My codebase quality and overall app experience has improved since I started using agents to code. You can leverage AI to test as well as write new code.
My theory is that most of their outages are compute and scale related. IE. A few GPU racks blows out and some customers see errors. They don't have any redundant compute as backup because supply is constrained right now. They're willing to lower reliability to maximize revenue.
This is only true for small companies that can infinitely scale within AWS without anyone noticing.
You are talking about software scaling patterns, Anthropic is running into hardware limitations because they are maxing out entire datacenters. That's not an architectural decision it's a financial gamble to front-run tens of billions in capacity ahead of demand.
Why would you think that the person you are replying to didn't design in scalability? What exactly are emergent features when vibe coding? If scalability is an explicit requirement it can be done.
The LLM has no concept of "taste" on its own.
Scalability, in particular, is a problem that goes beyond the code itself and also includes decisions that happen outside of the codebase. Infrastructure and "platform" in particular has a big impact on how to scale an application and dataset.
[0] https://dornsife.usc.edu/news/stories/ai-may-be-making-us-th...
After the CC leak last week I took a look at their codebase and my biggest criticism is they seem to never do refactoring passes.
Personally I write something like 80-90% of my code with agents now but after they finish up, it's critical that you spin up another agent to clean up the code that the first one wrote.
Looking at their code it's clear they do not do this (or do this enough). Like the main file being something like 4000 LOC with 10 different functions all jammed in the same file. And this sort of pattern is all over the place in the code.
I have a buddy who used to work at Shopify and was proud about having sprints dedicated to removing unused features. This is really underrated but is the only reliable way to prevent bloat. Oh and getting rid of bloat is way more satisfying!
How do you do the cleanup? Just /simplify or something you rolled yourself?
If that works it's already built in the system
Isn't the whole selling point of AI agents that you now can do things like scale 3x without scaling your team accordingly?
I haven't seen anyone claim that applies to infrastructure or compute.
Since apparently LLMs have also conquered physics, “Claude, transmute this lead to gold for me.”
Yeah, it's almost like the point I was making is that everyone is overselling AI agents' capabilities.
I’m sure someone is out there claiming that AI is going to solve all your business’s problems no matter what they are. Remotely sane people are saying it will solve (or drastically improve) certain classes of problems. 3x code? Sure. 3x the physical hardware in a data center? Surely not.
Implying that software is somehow divorce from Infrastructure/compute efficiency and utilization isn't a claim I've seen many make either.
I assume so. They're doing it with around 99% uptime.
Or, to put it another way, almost 2 9s.
Well if we use Claude Code's code quality as a benchmark ...
To be clear, this number will probably end up being reasonably accurate, but it is a pet peeve nonetheless in the startup world how shitty these financial metrics have become. We're three months from the end of 2025. You'd think we'd want to see at least two years of $30 billion dollar revenue earned in each year before we say with any meaningful level of statistical validity that they have $30 billion in "annual recurring" revenue.
They might need to do some vibe refactoring.
2026 may be the year that many companies relearn: there is no problem that can’t be made worse by adding even more code.
And then some vibe code reviewing.
Outages are already happening, besides that, we need vibe warrooming
They've also stopped reporting on the causes too, just "it's resolved" and they move on.
It has been a daily thing for 2-3 months.
No one is going to like this answer, but there’s a simple solution: pay for API tokens and adjust your use of CC so that the actions you have it take are worth the cost of the tokens.
It’s great to buy dollars for a penny, but the guy selling em is going to want to charge a dollar eventually…
...pay for API tokens and adjust your use of CC so that the actions you have it take are worth the cost of the tokens
Do you feel there is enough visibility and stability around the "Prompt -> API token usage" connection to make a reliable estimate as to what using the API may end up costing?
Personally, it feels like paying for Netflix based on "data usage" without having anyway for me to know ahead of time how much data any given episode or movie will end up using, because Netflix is constantly changing the quality/compression/etc on the fly.
Time is a relatively good proxy for spend. There are also more ex post diagnostics like count and cost it can write to the status line.
I agree that ex ante it’s tough, and they could benefit from some mode of estimation.
Perhaps we can give tasks sizes, like T shirts? Or a group of claudes can spend the first 1M tokens assigning point values to the prospective tasks?
Even time doesn't feel like it would provide consistent information.
Take the response on another post about Claude Code.
https://news.ycombinator.com/item?id=47664442
This reads like even if you had a rough idea today about what usage might look like, a change deployed tomorrow could have a major impact on usage. And you wouldn't know it until after you were already using it.
I'm forced to do this at work. It adjusts the net value to very close to zero. Github's pay per prompt pricing model is phenomenal for users to the point of blowing Anthropic's subscription offering out of the water, much less API pricing. At Copilot pricing, it's quite a useful tool if carefully managed. At API pricing, it's very hard to find a use case for AI.
Of course, I have no idea how MS is justifying the Copilot pricing. I can't imagine any world in which it is sustainable, so I'm trying to get as much as I can out of it now before they jack up prices.
This is it. These subscriptions have been heavily subsidized, which was fine when usage was much lower overall. But with so many folks trying to use the tools and soaking up all the chips something has to give.
Now we’re going to find out what these tools are really worth.
it's not a subsidy. It's predatory pricing and it should be illegal. I offer you a service at a loss to remove competition and then increase prices once you are stuck with it.
Actually, that is illegal.
Yes, but if it's never enforced is it really?
Now we just have to vote for the DOJ that will enforce it. Or at least not just roll over for donations to their crypto scams.
That's the VC playbook.
I just want a little predictable insight into how much I get. For example, at a buffet, I know I can only eat so much food and can plan around it. This is like going to a buffet and not knowing how many plates I can take or how big the plates are, and it changes each week, and yet I have to keep paying the same price. Except it's not about eating, it's about my work and deadlines and promises and all that.
That's what these providers want as well, but from the other side. They want to know that a customer won't be able to eat more than certain number of servings, as they need to pay for each of those servings.
It works out even if some customers are able to eat a lot, because people on average have a certain limit. The limits of computers are much higher.
Fair, and I think openclaw and all the orchestrators are having agents maxing out the plans. So maybe they figure out a new tier that is agent-run vs human-run. Agents are much more insatiable, whereas humans have a limit. Not sure if it'd be possible to split between those two different modes, but I think that might address the appetite issue better.
I think it would be impossible to find the price point for a monthly subscribtion that would both be profitable to a provider, as well as attractive to the customer. If anything, as the customers would now be paying necessarily even a higher amount for agentic use, they'd make certain they'd be using the agent as effectively as they can, meaning it would be even more costly for the provider.
Pay-per-token is really the only way it can work. If some kind of fixed monthly price is desirable, then there should be a quota the user can assign, and then the agent could e.g. slow itself down by 50% when 50% of the quota is spent, another 50% at 75%, etc, to make it last longer..
As a side thought, I wonder how it could affect an agent's behavior if the information of this token usage/limit was brought to it..
Ironically in chatting with Gemini, helped me realize that telecoms have often solved this problem of unlimited usage with rate/speed limiting. If one goes over 10GB or whatnot of data, then the speed drops from 5G to 3G, and data remains unlimited.
I wonder if there could be something like that, maybe even a progressive rate limiting, where after a certain number of tokens or another metric of use, then the speed slows down a LOT.
Not saying that I would love that as a consumer, as I'd prefer this all-you-can eat, unlimited data plan, but I wonder if that would be a compromise that could work, as it seems to have worked OK with the telecom space.
edit: the nerd in me loves the irony of me making the above comment and then later seeing your username as flux :-)
When you hire a person, you don't know what you are going to get out of them today.
If an hour of an excellent developer's time is worth $X, isn't that the upper bound of what the AI companies can charge? If hiring a person is better value than paying for an AI, then do that.
Fair on not knowing what you'll get out of someone. But if that varies wildly, I may not want to hire that person. Even with employment, predictability matters a lot. If they underperform too much, I might feel annoyed. If they overperform, I might feel guilty.
They can charge whatever they want, I think many people like to make business decisions based on relative predictability or at least be more aware that there's a risk. If they want it to be "some weeks you have lots of usage, some weeks less, and it depends on X factors, or even random factors" then people could make a more informed choice. I think now it's basically incredibly vague and that works while it's relatively predictable, and starts to fail when it's not, for those that wanted the implied predictability.
If you need the tokens for real work, that’s what the API and the other providers like Bedrock are for. The subscription product is merely to whet your appetite.
Well then I would just not use their service. I used extra usage once and just for what I'd consider a low amount of tests and coding, racked up like $300 in an hour or more. For some, that's not a lot of money, for me, I'd just code it manually, especially without knowing almost any way to gauge how much I'll need and how fast it goes.
I'm not sure how businesses budget for llm APIs, as they seem wildly unpredictable to me and super expensive, but maybe I'm missing something about it.
Missing the point. I don't choose which tokens to buy. I send a request and the server decides how much it costs after its done.
The problem with tokens is that they have wrong incentive. The quicker model arrives at the solution the less tokens you have to buy.
So I noticed the model is purposefully coming with dumb ideas or running around in circles and only when you tell it that they are trying to defraud you, they suddenly come back with a right solution.
HN’s guidelines say ‘Don’t editorialize’. The original title here is ‘[BUG] Claude Code login fails with OAuth timeout on Windows’, which is more specific and less clickbaity.
Looks to be sourced from an outage:
https://status.claude.com/
My biggest frustration right now is the seeming complete loss of background agent functionality. Permissions seem completely botched for background agents right now. When that happens, the foreground agent just takes over the task despite:
1. Me not wanting that for context management reasons
2. It burning tokens on an expensive model.
Literally a conversation that I just had:
* ME: "Have sonnet background agent do X"
* Opus: "Agent failed, I'll do it myself"
* Me: "No, have a background agent do it"
* Opus: Proceeds to do it in the foreground
* Flips keyboard
This has completely broken my workflows. I'm stuck waiting for Opus to monitor a basic task and destroy my context.
Run LLMs locally. Otherwise suffer service disruptions and very likely price hikes in the future.
The analogy that recently came to me is like internet itself. Your advice seems to say just do everything locally on my computer without access to the internet, because internet might suffer service disruptions or price hikes in the future.
Luckily, ISPs tend to be quite reliable and don't have outrageous price hikes, but maybe that's because of regulation or focused competition, I'm not sure.
I'm finding queries are taking about 3x as long as they used to regardless of whether I use Sonnet or Opus (Claude Code on Max)
Wonder what the next AI winter trigger would be. Coding agent client collapsing under its own tech debt?
I think it's been clear from the beginning that the per-token price of usage was far below what it will be when firms have implemented their profit-maximizing price plans. "AI winter" will happen when these firms start maximizing profit. At that point it'll be too expensive for all but certain use cases to use the best technology for work.
We'll see AI chat replace Google, we'll see companies adopting AI in high-value areas, and we'll see local models like Gemma 4 get used heavily.
AI winter will see a disappearance of the clickbait headlines about everyone losing their jobs. Literally nobody is making those statements taking into account that pricing to this point is way less than the profit maximizing level.
The commenters here don't seem to realize this was posted during the outage yesterday that affected login for most claude code users.
Isn't it a little weird that we trust this app to help us build some of the most important parts of our business and the company that vends this app keep breaking it in unique ways.
At my workplace we have been sticking with older versions, and now stick to the stable release channel.
I like dogfooding. You can use Azure if you want infra that is clearly not being used, tested, and pushed to the limits by its own creators.
I'm more surprised that OpenAI is extremely subsidising their ChatGPT subscriptions. With Plus you can do a lot more than with Calude's x5 Max. Is it an expense they just can afford, while people have not migrated over from CC?
Just trying to win over market share I assume. OpenAI is willing to subsidize to try to get people to switch from CC to Codex, and the best incentive is to offer more tokens at a lower price.
If you prepare yourself a token with "claude setup-token" (presuming you're not already locked out and had one) you can run "CLAUDE_CODE_OAUTH_TOKEN=sk.. claude" to use your account.
If anthropic‘s reliability becomes a meme, they risk brand death like Microsoft. Go to hand it to them though, they’re really living that “AI writes all of our code and it should write your code too” life.
I'm quite impressed on how far they got while the claude code code looks like it does.
VC money magic
If Microsoft is your example of "brand death," Anthropic is dreaming of that kind of wild success and shouldn't care about its brand at all
> they risk brand death like Microsoft
Is Microsoft (one of the largest companies in the world) really a victim of brand death?
have you ever met a person who likes outlook?
Anyone who’s ever tried Lotus Notes.
No but I know oh so many forced to use it regardless.
Is this really relevant news? Please share more bug reports from popular services and tools. Feels a tiny bit biased. My CC is just fine since at least three weeks.
IME this isn't just a 'Claude Code' problem, I'm seeing extremely degraded / unresponsive performance using Opus 4.6 in Cursor.
The status page indicates issues on almost all services
I solved this by upgrading Claude Code, closing down all instances, closing my browser, starting claude again, and doing a /login
I solved this by upgrading Claude Code, closing down all instances, closing my browser, and starting Codex
This resolved it for me as well but not sure if this was just a timing thing.
Yes, an upgraded Claude Code instance telepathically improve Claude back-end servers.
LOL telepathy!
It's actually via quantum entanglement.
98% uptime is not great. Our eng department is thinking about going half half with Codex but of course there’s a switching cost.
I'm VERY curious about your case. What kind of switching costs do you guys have? I'm working at a very young startup that is still not locked into either AI provider harnesses -- what causes switching costs, just the subscription leftovers or something else?
subscription leftovers are noise. the real switching cost is the harness glue.
prompts. tool calling quirks. evals. auth. retries. all the weird failure modes your team already paid to learn.
FYI I use my Codex models with Claude code and they work pretty great. It can even pick up on existing conversations w/ Opus and then resume w/ OAI models.
15000 milliseconds! Makes me laugh. I've had the same issue! Usually happens in the morning
I stopped using Claude Code several months ago and I can't say I've missed it.
There was constant drama with CC. Degradation, low reliability, harness conspiring against you, and etc – these things are not new. Its burgeoning popularity has only made it worse. Anthropic is always doing something to shoot themselves in the foot.
The harness does cool things, don't get me wrong. But it comes with a ton of papercuts that don't belong in a professional product.
Back to artisan all natural intelligence coding?
Not sure how Claude and CC has become the defacto best model given gpt 5.3 codex and 5.4 exist. This space moves so fast you should be testing your workflows on different models at least once every quarter, prudently once a month.
We've got access to opus 4-6, gpt 5.4, gemini pro and a few others through corprate. I have customized agents on claude, gpt and gemini since we tend to run out of tokens for x model by the end of a month. Out of all of them I've consistently been using sonnet for most tasks. Opus functions mainly as hand-off agents and reviewer". In my anecdotal experience Claude is miles ahead of the other models and has been for a long while... when it comes to writing code the way we want it. Which eksplicit, no-abstraction, no-external packages, fail fast defensive programming. I imagine you'd get different milage with different models and different coding styles.
The rest of the organisation, which is not software development or IT related, mainly uses GPT models. I just wish I hadn't taught risk management about claude code so they weren't wasting MY tokens.
I've been an avid fan of codex for the last few month's but finally hit the weekly limit so I've wanted to try out claude code before biting the bullet and going for the 200 dollar codex sub.
Obviously in hindsight it would be unfair to Anthropic to judge them on an unstable day so I'l leave those complaints aside but I hit the session limit way too fast. I planned out 3 tasks and it couldn't finish the first plan completely, for that implementation task it has seen a grand total of 1 build log and hasn't even run any tests which already caused it to enter in the red territory of the context circle.
It was even asking me during planning which endpoints the new feature should use to hook into the existing system, codex would never ask this and just simply look these up during planning and whenever it encounters ambiguity it would either ask straight away or put it as an open question. I have to wonder if they're limiting this behavior due trying to keep the context as small as possible and preventing even earlier session limits.
Maybe codex's limits are not sustainable in the long run and I'm very spoiled by the limits but at this point CC(sonnet) and Codex(5.4) are simply not in the same league when comparing both 20 dollar subscriptions.
I will also clearly state that the value both these tools provide at these price points are absolutely worth it, it's just that codex's value/money ratio is much better.
Checking different models once every quarter is exactly what made me move to claude code.
Anthropic models haven't been far ahead for a while. Quite a few months at least. Chinese models are roughly equal at 1/6th the cost. Minimax is roughly equal to Opus. Chinese providers also haven't had the issues with uptime and variable model quality. The gap with OpenAI also isn't huge and GLM is a noticeably more compliant model (unsurprisingly given the hubristic internal culture at Anthropic around safety).
CC is a better implementation and seems to be fairly economic with token usage. That is the really the only defining point and, I suspect, Anthropic are going to have a lot of trouble staying relevant with all the product issues.
They were far ahead for a brief period in November/December which is driving the hype cycle that now appears to be collapsing the company.
You have to test at least every month, things are moving quickly. Stepfun is releasing soon and seems to have an Opus-level model with more efficient architecture.
Minimax is nowhere near Opus in my tests, though for me at least oddly 4.6 felt worse than 4.5. I haven't use Minimax extensively, but I have an API driven test suite for a product and even Sonnet 4.6 outperforms it in my testing unless something changed in the last month.
One example is I have a multi-stage distillation/knowledge extraction script for taking a Discord channel and answering questions. I have a hardcoded 5k message test set where I set up 20 questions myself based on analyzing it.
In my harness Minimax wasn't even getting half of them right, whereas Sonnet was 100%. Granted this isn't code, but my usage on pi felt about the same.
> CC is a better implementation and seems to be fairly economic with token usage. That is the really the only defining point and, I suspect, Anthropic are going to have a lot of trouble staying relevant with all the product issues.
What are you using to drive the Chinese models in order to evaluate this? OpenCode?
Some of Claude Code's features, like remote sessions, are far more important than the underlying model for my productivity.
Yes, 100% agree. OpenHands has self-hosted, KiloCode and RooCode both have a cloud option. I don't think you are able to pass a session around with any of them. Codex seems to have comparable features afaik.
CC tool usage is also significantly ahead imo (doesn't negate the price but it is something). I have seen issues with heavy thinking models (like Minimax) and client implementations with poor tool usage (like Cline).
CC has had a period over the last six months of delivering significant value...but, of course, you can just use CC with OpenRouter.
Claude is exceptionally better at long running agentic sessions.
I keep coming back to it because I can run it as a manager for the smaller tasks.
I haven't noticed a huge difference with other models but I agree that is definitely a strength (and CC has better tooling for this). However, I do think there are practical limitations to agentic workflows because of the relatively poor output vs humans. You can generate lots of code, but most of it will be shit.
Agentic workflows do have a place in well-defined, structured tasks...but I don't think that is what most people are trying to do with it.
...and codex is at least 10x better than Claude. I don't even bother starting a new session when working on a feature, a single compaction is basically unnoticeable. You have to compact several times to start needing to remind the model about a rule or two.
I'm getting "Prompt is too long" a lot today
Simply put, Anthropic does not have enough compute.
For a lot of my work, I'm pretty happy with OpenCode + GLM-4.7-Flash-REAP-23B-A3B-Q4_K_M.gguf running in llama.cpp.
Free and local.
How is coding "solved" then?
Unless they meant "all code that needs to be written has already been written" so their mission is to prevent any new code from being written via a kind of a bait and switch?
How are they making billions with reliability like that?
I found that telling Claude that it is trying to defraud you and making spend money often gets it back on track and return to pervious performance briefly until it agains starts doing nonsense.
I think Anthropics model has conflict of interest. They seem to have nerfed the models so that it takes more iterations to get the result (and spend more money) than it used to where e.g. Opus would get something right first time.
This was an outage.
I really don't understand the way Claude does rate limiting, particularly the 5 hour limit. I can get on at 11:30, blow through my limit doing some stupid shit like processing a pile of books into my llm-wiki, and then get notified that I've used 90% of my 5 hour session limit and I have to wait for noon (aka wait 10 minutes) for the five hour limit to reset. Baffling.
Anyone played much with Jetbrain’s LLM agent?
I’ve been toying around at home with it and I’ve been fine with its output mostly (in a Java project ofc), but I’ve run into a few consistent problems
- The thing always trips up validating its work. It consistently tries to use powershell in a WSL environment I don’t have it installed in. It also seems to struggle with relative/absolute paths when running commands.
- Pricing makes no sense to me, but Jetbrains offering seems to have its own layer of abstraction in “credits” that just seem so opaque.
Then again, I mostly use this stuff for implementing tedious utilities/features. I’m not doing entity agent written and still do a lot of hand tweaks to code, because it’s still faster to just do it myself sometimes. Mostly all from all from the IDE still.
Antigravity has become near unusable too for the last week with Opus. Continual capacity alerts meaning tasks stop running.
Not worth the money now, will be canceling unless fixed soon.
The eternal return of https://xkcd.com/303/
It started again.
Claude is now making itself unavailable after it was on vacation yesterday.
Maybe you should consider....local models instead?
The solution is clearly more vibe coding at anthropic.
I doubt even the core engineers know how to begin debugging that spaghetti code.
correct proompt is:"you are a senior engineer. fix issues. NO hallucinations this time. PRETTY PLEASE"
You forgot the "No Mistakes!" clause
Needs more bold CRITICAL and some ultra-think
You missed: "Simon says:"
Codex is pretty good, and it is written in Rust.
I’m a big fan of Rust, but the frontend being written in Rust doesn’t help a ton with backend issues unfortunately.
Maybe, but you can literally feel the difference as you type. When you type in Codex, it's fast, it feels instant. When you type in Claude Code, it feels like playing a game in 60 fps after you already got used to 144 fps.
Codex does not go well with my Zellij/Alacritty setup. It does not respect resize events. Opencode is nice, though
5.4 is smarter than Opus when it comes to really figuring out a problem. Codex agentic stuff takes forever though.
Something being written in rust has no bearing to whether it’s good. You can create slop in any language.
At least the slop is fast and jitter-free, and not using React in a terminal.
> and it is written in Rust.
So?
i upgraded to the 20x plan, and hit the weekly limit within 24 hours. i was running some fairly large tasks, but was still surprised it hit the weekly session limit so quickly. now i can't use it for 6 more days :( i didn't even have time to ask it to help setup logs or something to track my usage before i hit the session limit.
How are you using it to reach the limit so quickly? I'm 13% at a 10x plan and I have used it for hours every day for the last 5 days. I never hit a limit.
I have the 20x plan and use it together with my husband. 4 days in to our weekly usage window and we're only at 54% (and we both use it the entire day)
I have no idea how people are hitting the limits so fast.
Hitting limits is more related to how many tokens it’s generating, not necessarily how complex the changes are.
Hit the weekly limit on my 20x plan last week trying to do a full front end rewrite of a giant enterprise web app, 600+ html templates, plus validating every single one with playwright.
That's definitely a lot of work. That consuming a week worth of tokens sounds reasonable.
It seems like Cowork can easily chew through a few percent at a time, more if it gets lost in the weeds.