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 Hack Sparks Concerns Over AI Security Risks(2 posts)→
More from AGI Musings
- Open-network research can reveal how a place looks to machines, not people — schwentker · 2026-07-24
- Conference slide says Graeme Segal is the mathematician AI will replace last — AlexKontorovich · 2026-07-24
- Charliermarsh: It's Worth Learning Things Useful Today Even If Obsolete Tomorrow — charliermarsh · 2026-07-24
- A new AI-era bottleneck is the physical world, not idea generation — xiao_ted · 2026-07-24
- A model screenshot argues the real problem is turning intelligence into agency — MoonL88537 · 2026-07-24
- AI’s underrated third use case may be contract formalization and negotiation — curious_vii · 2026-07-24