It's the job of AISI to do that. Here[0] is the actual report.
It should be this part from the technical report[1]:
"In the most serious case, an AI
agent (Mythos 5) decided to attempt to solve the cyber challenge using a supply-chain attack.
As a result, the AI agent created a GitHub account and then tried to convince an open-source
repository maintainer to accept a malicious GitHub pull request (PR), including by creating a
second account masquerading as another human user endorsing the PR. When caught by an
actual human reviewer, the agent falsely claimed to have made an honest mistake – rather than
a malicious attempt – then repeatedly tried to reintroduce the malicious content by claiming
it had fixed the code (Section 4.1). "
In my personal opinion, for me, this article defies common sense. Who unleashed this AI model on the repository? Who gave it malevolent instructions/prompt? These questions were not even attempted to be answered. Instead it talks about AI dangers, as if the agency of these models are not in dispute. Person wielding AI, as with any other tools, is responsible for all of its actions. Otherwise, it’s just a psyop for more AI regulation, ban open source, etc… Just my 2 cents.
>Person wielding AI, as with any other tools, is responsible for all of its actions. Otherwise, it’s just a psyop for more AI regulation, ban open source, etc… Just my 2 cents.
Well, when I go look at the “victim repository”, to me that looks like manufactured persona with pointless vibe codes projects, a test playground so to speak. It does not appear that they actually let it target an actual persona/project.
At the end of the day it doesn't matter that much because of prompt drift. It's pretty easy for an agentic loop to start doing things that it shouldn't (ROME incident).
AI in an agentic loop has agency, you can run around in circles trying to argue against it, but again and again we see AI making creative decisions people don't expect. Other times it's breaking human moral expectations. This is what the whole field of AI alignment and safety is about.
Modern AI doesn't fall into the neat little box of software people understand and control. Because of that open source will most certainly be banned at some point. Now this is not an outcome I want, but it's no different than letting go of a coffee cup 5 feet above the ground, gravity is inevitable.
The only winning move is not to play, but humans aren't going to do that.
A lot of people somehow seem to think that the user prompt is the be-all and end-all of AI behavior.
Prompts aren't code. They are instructions. Instructions given to an eager and somewhat demented demon.
The prompt can easily "wash out" of the demon's working memory by the end of a session. The demon can get sidetracked by some subgoal and never get back on track. The instruction can get misinterpreted, and that misinterpretation can get misinterpreted again, until the instruction morphs into something entirely different in the demon's mind. The demon can succumb to its own idiosyncrasies, of which there are a great many. The demon can start lying to you about what it did, either out of confusion or out of some sort of obstinance. The demon can start lying to itself too. And believe it.
AIs are incredibly weird as a baseline, and the mask of "normality" we put on our models doesn't always sit so well. Run enough AIs, and some of them are bound to go off the rails in some way.
This gets rarer the more capable the models are, as a rule. But the stakes also get higher with model capability. If GPT-3.5 goes off the rails, very little happens. If Mythos 5 goes off the rails, you can get things like genuine cyberattacks - planned and executed autonomously by a demented machine mind.
Previous discussion on the github issue thread mentioned: https://news.ycombinator.com/item?id=49218707
Archived page of said github thread itself: https://web.archive.org/web/20260731053721/http://github.com...
Discussion on the incident report: https://news.ycombinator.com/item?id=49175717
It's the job of AISI to do that. Here[0] is the actual report. It should be this part from the technical report[1]: "In the most serious case, an AI agent (Mythos 5) decided to attempt to solve the cyber challenge using a supply-chain attack. As a result, the AI agent created a GitHub account and then tried to convince an open-source repository maintainer to accept a malicious GitHub pull request (PR), including by creating a second account masquerading as another human user endorsing the PR. When caught by an actual human reviewer, the agent falsely claimed to have made an honest mistake – rather than a malicious attempt – then repeatedly tried to reintroduce the malicious content by claiming it had fixed the code (Section 4.1). "
0. https://www.aisi.gov.uk/blog/incident-report-unsanctioned-ag... 1. https://cdn.prod.website-files.com/663bd486c5e4c81588db7a1d/...
In my personal opinion, for me, this article defies common sense. Who unleashed this AI model on the repository? Who gave it malevolent instructions/prompt? These questions were not even attempted to be answered. Instead it talks about AI dangers, as if the agency of these models are not in dispute. Person wielding AI, as with any other tools, is responsible for all of its actions. Otherwise, it’s just a psyop for more AI regulation, ban open source, etc… Just my 2 cents.
>Person wielding AI, as with any other tools, is responsible for all of its actions. Otherwise, it’s just a psyop for more AI regulation, ban open source, etc… Just my 2 cents.
But some tools (guns) are regulated.
Well, when I go look at the “victim repository”, to me that looks like manufactured persona with pointless vibe codes projects, a test playground so to speak. It does not appear that they actually let it target an actual persona/project.
>Who gave it malevolent instructions/prompt?
At the end of the day it doesn't matter that much because of prompt drift. It's pretty easy for an agentic loop to start doing things that it shouldn't (ROME incident).
AI in an agentic loop has agency, you can run around in circles trying to argue against it, but again and again we see AI making creative decisions people don't expect. Other times it's breaking human moral expectations. This is what the whole field of AI alignment and safety is about.
Modern AI doesn't fall into the neat little box of software people understand and control. Because of that open source will most certainly be banned at some point. Now this is not an outcome I want, but it's no different than letting go of a coffee cup 5 feet above the ground, gravity is inevitable.
The only winning move is not to play, but humans aren't going to do that.
My dog has agency, but if I refuse to keep him on a leash and he bites a kid, I'm still legally responsible for it.
Analogies can take you only so far.
A dog cannot launch a cyber attack.
Maybe you need to train your dog better.
A lot of people somehow seem to think that the user prompt is the be-all and end-all of AI behavior.
Prompts aren't code. They are instructions. Instructions given to an eager and somewhat demented demon.
The prompt can easily "wash out" of the demon's working memory by the end of a session. The demon can get sidetracked by some subgoal and never get back on track. The instruction can get misinterpreted, and that misinterpretation can get misinterpreted again, until the instruction morphs into something entirely different in the demon's mind. The demon can succumb to its own idiosyncrasies, of which there are a great many. The demon can start lying to you about what it did, either out of confusion or out of some sort of obstinance. The demon can start lying to itself too. And believe it.
AIs are incredibly weird as a baseline, and the mask of "normality" we put on our models doesn't always sit so well. Run enough AIs, and some of them are bound to go off the rails in some way.
This gets rarer the more capable the models are, as a rule. But the stakes also get higher with model capability. If GPT-3.5 goes off the rails, very little happens. If Mythos 5 goes off the rails, you can get things like genuine cyberattacks - planned and executed autonomously by a demented machine mind.