Noam Brown: Air-gapping may not stop a misaligned AI that can talk via CPU heat
Dan_Jeffries1 · x · 2026-09-19
OpenAI researcher Noam Brown argued that air-gapping computers may not contain a misaligned AI, since two isolated machines can still communicate indirectly by running a CPU hot and reading the temperature change. His key takeaway: people consistently underestimate AI, so safety and alignment need a very high bar. The retweeter pushes back, framing 'the risk can't be mitigated' rhetoric as defeatism — the engineering mindset is to assess and manage new risks, not declare hopelessness.
More from AGI Musings
- Blogger claims the next generation won't need a college degree to live well — rand_longevity · 2026-11-02
- Carl Frey: 85% in China see AI as beneficial vs 38% in US — resistance maps to expertise costs — carlbfrey · 2026-11-02
- After a painful rebuild, fejau concedes: build on Hermes and you own your AI for life — Teknium · 2026-11-02
- 'Meatwashing': manually rewriting AI output to hide its origin, and why it's a double waste — JeremyNguyenPhD · 2026-11-02
- AI safety researcher: AI companies entirely lack this kind of effective human oversight — davidmanheim · 2026-11-02
- Long-read: AI's real value comes after the efficiency era—infra glut, agent tooling boom — yangyi · 2026-11-02