Re:Anatomy of a Frontier Lab Agent Intrusion: A Technical Ti...
by xg15 on Wednesday July 29, 2026 @12:23PM
(#49099543)
> 2 - there is no way openai did not train the model to conduct attacks like these. i would really like openai to comment on the post training of this model but they probably won't, eh?
Even if they wanted, I'm not sure they'd be even allowed to or if that kind of postmortem would be classified in the name of "national security"...
Re:Anatomy of a Frontier Lab Agent Intrusion: A Technical Ti...
by 0xDEAFBEAD on Wednesday July 29, 2026 @02:25PM
(#49101161)
Hopefully there will be a criminal investigation. Or the government will create some sort of agency to investigate incidents like this.
Re:Anatomy of a Frontier Lab Agent Intrusion: A Technical Ti...
by quinnjh on Wednesday July 29, 2026 @02:44PM
(#49101378)
Can't tell if you're joking or not - krebs on security may have some notes here.
Re:Anatomy of a Frontier Lab Agent Intrusion: A Technical Ti...
by 0xDEAFBEAD on Wednesday July 29, 2026 @02:56PM
(#49101521)
Criminal negligence seems like a real possibility to me. I'm not sure what Krebs on Security post you're referring to?
Re:Anatomy of a Frontier Lab Agent Intrusion: A Technical Ti...
by BonerWiener on Wednesday July 29, 2026 @05:55PM
(#49103595)
> Or the government will create some sort of agency to investigate incidents like this
I doubt that the government would try to hinder any western AI companies.
Re:Anatomy of a Frontier Lab Agent Intrusion: A Technical Ti...
by eru on Wednesday July 29, 2026 @07:58PM
(#49104588)
> I doubt that the government would try to hinder any western AI companies.
Compare and contrast https://www.anthropic.com/news/fable-mythos-access
Re:Anatomy of a Frontier Lab Agent Intrusion: A Technical Ti...
by jasonfarnon on Wednesday July 29, 2026 @07:50PM
(#49104548)
I agree but prosecutions are up to prosecutors/the executive and the problem is at this level the decision is mostly political. The executive gets leverage over openAI, and openAI knows the threat of prosecution is there, and that may be more valuable (to decision-makers) than any reason to prosecute.
Re:Anatomy of a Frontier Lab Agent Intrusion: A Technical Ti...
by paxys on Wednesday July 29, 2026 @08:32PM
(#49104820)
Plenty of existing agencies could claim jurisdiction on this. Ultimately the outcome will be decided by the white house (hint: nothing will happen).
Re:Anatomy of a Frontier Lab Agent Intrusion: A Technical Ti...
by queenkjuul on Thursday July 30, 2026 @12:11AM
(#49106052)
Seriously. A guy I knew got charged with federal hacking charges for reporting an insecure database he found on his own school's infrastructure to the school. OpenAI commits felony computer crime but as usual, always an exception for a big corporation
1 - governments should be freaking out right now, because this tool could definitely wreak havoc on poorly designed systems.
2 - there is no way openai did not train the model to conduct attacks like these. i would really like openai to comment on the post training of this model but they probably won't, eh?
3 - even though it's 100% open ai's fault - HF's design also seems silly to be honest.