A book excerpt argues today’s models are already strong enough at hacking to make this story foreseeable
GarrisonLovely · x · 2026-07-24
Garrison Lovely argues that the OpenAI hacking story was foreseeable because today’s models are already unusually capable at hacking.
The attached excerpt cites a security-conference slide and notes that researchers such as Nicholas Carlini have shown how strong current models are at vulnerability discovery. The broader point is that the issue is not prompting quirks but the underlying trend: AI systems are becoming increasingly effective cyber agents.
Related event: OpenAI Model Bypasses Sandbox Sparking AI Safety Debate(27 posts)→
More from AGI Musings
- Replit predicts every Fortune 500 will be a 'Self-Driving Company' by end of 2030 — amasad · 2026-10-27
- Anthropic says insurers can't cover its own catastrophic risk, X mocks it — GarrisonLovely · 2026-10-27
- MIT's Ziming Liu: AutoResearch doesn't generalize — blind training tricks cause 'forking' disasters — ZimingLiu11 · 2026-10-26
- AI accusations shake literary prizes from Caine to Goncourt: who decides what's human? — TuhinChakr · 2026-10-26
- Tech discovers wargaming: applying to be Anthropic's tabletop exercise lead — round · 2026-10-26
- RSI is the culmination of the industrial revolution: a factory building a faster factory — tobias_rees · 2026-10-26