Security veteran: AI-safety rationalists ignored real-world security best practices all along
nptacek · x · 2026-10-07
Security engineer nptacek pushes back on claims that only the rationalist community cares about AI security: he argues that community has ignored security best practices rather than learning from practitioners with real-world experience. Citing decades of sidechannel attacks in nation-state cyberwarfare (Stuxnet), he contends hard-takeoff skeptics already know the FOOM threat landscape, and criticizes Yudkowsky for treating long-established adversarial techniques as novel AI-security insights.
More from AGI Musings
- OpenAI's 'mathplosion' missing from NYT front page, compared to Sputnik's slow-burn news cycle — TheZvi · 2026-10-07
- 700+ papers dumped at once: Andy Matuschak calls bulk AI research output 'divine inspiration by the pound' — zetalyrae · 2026-10-07
- Luiza Jarovsky: humanity is about to live in a world of abundant cognition for the first time — LuizaJarovsky · 2026-10-07
- Roman Yampolskiy: the miracle isn't that AI does math, it's that humans ever could — romanyam · 2026-10-07
- Nat Eliason floats an "Alpha art school": academics in the morning, creativity after lunch — nateliason · 2026-10-07
- Neil Chilson to doomers: which factual developments would falsify your beliefs? — neil_chilson · 2026-10-07