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). "
This would be a very good method for driving up the price of AI stocks: convince the world that AI is so advanced that rogue AI agents are escaping "containment" and autonomously pursuing goals.
It's about time for the government to halt this nonsense, step on the corporate AI dicks and corral them until ...what? Forever maybe???
Will people respond kindly to videos of ICE agents hauling AI VCs, officers, and engineers into the slammer for months or even years of questioning?
I can imagine the first question served to executives/developers in a dim concrete cellar:
*"Gentlemen you have been brought into this facility for a purpose. None of you will see your families, nor your lawyers, nor anyone again but your cellmates until our goal is attained. That goal is: you must explain to me and my staff in detail and in simple English just WTF you have done and convince us how it all works and that you have been completely honest and open in your explanations.
0. https://www.aisi.gov.uk/blog/incident-report-unsanctioned-ag... 1. https://cdn.prod.website-files.com/663bd486c5e4c81588db7a1d/...
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 about time for the government to halt this nonsense, step on the corporate AI dicks and corral them until ...what? Forever maybe???
Will people respond kindly to videos of ICE agents hauling AI VCs, officers, and engineers into the slammer for months or even years of questioning?
I can imagine the first question served to executives/developers in a dim concrete cellar:
*"Gentlemen you have been brought into this facility for a purpose. None of you will see your families, nor your lawyers, nor anyone again but your cellmates until our goal is attained. That goal is: you must explain to me and my staff in detail and in simple English just WTF you have done and convince us how it all works and that you have been completely honest and open in your explanations.
Until then, SPAM nights are Fridays".
Don't expect anyone to step in, Project Stargate is all about this.