Altman: models will find bugs 'outside the normal threat model' and patching won't save us
wfithian · x · 2026-10-28
OpenAI CEO Sam Altman says he doesn't "even know a dramatic enough word" for the security risk ahead: models will be able to find bugs beyond the normal hacker threat model, including "hardware-level, insane stuff" — and he no longer believes we can just patch all the bugs. Resharing it, Peter Wildeford pointedly notes the problem is one OpenAI itself created and keeps accelerating.
More from AGI Musings
- DeepMind researcher: all of mathematics will soon be formalizable, with agents hunting proofs — ChrSzegedy · 2026-10-28
- AI reply bots are degrading X discourse, a 'Gresham's Law' for social replies — generativist · 2026-10-28
- Be prepared: your life's research problem could be solved by a stranger's idle AI prompt on a commute — fkasummer · 2026-10-28
- A fine-tuned 'cat obsession' control fools every AI welfare criterion — MirrorEthic_Anchor · 2026-10-28
- OpenAI researcher: frontier AI ideas can't be patched for safety after the fact — willdepue · 2026-10-28
- Big Short's Eisman: the whole market is now 'one trade' on AI — and it 'better succeed' — SumitGup · 2026-10-28