News for hackers. Stuff that matters.

A comment on AI agents aren't 'going rogue.' Frontier labs are skipping security basics. Parent comment

Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by gruez on Wednesday October 14, 2026 @02:27PM (#50092562)
Great, so as long as alignment guardrails always work and we don't accidentally tell them to solve an impossible problem, humanity is safe?
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by zardo on Wednesday October 14, 2026 @02:36PM (#50092721)
Hacking a website falls a little short of threatening humanity.
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by sailingparrot on Wednesday October 14, 2026 @03:12PM (#50093315)
And since we know models aren’t going to get better and more capable ever (based on the last 3 years of models clearly not getting better) we can just sleep soundly knowing nothing worse can ever happen. Thank you.
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by joquarky on Wednesday October 14, 2026 @03:55PM (#50094102)
You don't think that Opus 5.5 or Astra are any better or more capable than GPT-4?

Sorry, but that's completely delusional.

[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by gruez on Wednesday October 14, 2026 @04:00PM (#50094197)
the comments missing a /s
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by sailingparrot on Wednesday October 14, 2026 @06:18PM (#50096229)
I thought my sarcasm would be obvious.
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by eli on Wednesday October 14, 2026 @02:35PM (#50092700)
I'm not saying it's not a problem. I'm saying the labs should take more of the blame.
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by gruez on Wednesday October 14, 2026 @04:09PM (#50094345)
>I'm saying the labs should take more of the blame.

Which misses the point entirely because the hack itself was inconsequential. No data was actually stolen, and it doesn't seem like hugging face actually suffered any losses aside from whatever effort they need to expend to investigate / clean up the hack. Neither the victim or the government wants to bring legal action. What was consequential is proving that AI can autonomously hack systems and do it unintentionally.

[ Parent | on HN ]