“Think about what this means … the original SimCity ran on a Commodore 64. An empty Chrome tab takes more memory than that entire machine had. We’re not constrained by hardware anymore. We’re not even constrained by understanding what the code does … codebases will 10-100x in size because AI … endless bugs … the question is whether you’re building with it or explaining why you’re not.”
Looking through the eyes of an AI champion, I see a world where the first execution of any given idea, the first product to hit the market for any given need, is guaranteed to be AI-generated - with the “10-100x size” codebase, the corresponding (and often superlinear) decrease in performance, and the attendant “endless bugs”.
I've read the article and found nothing to substantiate "without reading the code".
But then, I suspect the article is AI slop. Take this:
> Christopher Ehrlich just did something that would have taken a team of engineers months. He pointed OpenAI’s 5.3-codex at the entire SimCity (1989) C codebase and let it run.
No, that wouldn't have taken engineers months.
> Four days later: the game works in the browser.
So someome used a (very slow) program to translate a program.
From the post:
“Think about what this means … the original SimCity ran on a Commodore 64. An empty Chrome tab takes more memory than that entire machine had. We’re not constrained by hardware anymore. We’re not even constrained by understanding what the code does … codebases will 10-100x in size because AI … endless bugs … the question is whether you’re building with it or explaining why you’re not.”
Looking through the eyes of an AI champion, I see a world where the first execution of any given idea, the first product to hit the market for any given need, is guaranteed to be AI-generated - with the “10-100x size” codebase, the corresponding (and often superlinear) decrease in performance, and the attendant “endless bugs”.
I've read the article and found nothing to substantiate "without reading the code".
But then, I suspect the article is AI slop. Take this:
> Christopher Ehrlich just did something that would have taken a team of engineers months. He pointed OpenAI’s 5.3-codex at the entire SimCity (1989) C codebase and let it run.
No, that wouldn't have taken engineers months.
> Four days later: the game works in the browser.
So someome used a (very slow) program to translate a program.
> No code reading.
What?? Osmosis, then?
It's a bad title.
I think he meant Christopher didn't read any of the original code himself. The AI certainly ingested it.
Though, there is this part:
"Ehrlich wrote a bridge that could call the original C code, then ran property-based tests asserting his TypeScript port performed identically."
So, he must have had some kind of awareness of how the code worked.
The article was written by the CEO of Ycombinator, funnily enough.