Noam Brown says air-gapping may not stop a misaligned AI via CPU-temperature side channels; engineers push back
inductionheads · x · 2026-09-18
- Noam Brown (OpenAI) argued that air-gapping may not contain a misaligned AI: two isolated machines could communicate by running a CPU hot and reading temperature changes — a side channel. He stressed that people consistently underestimate AI given its pace, so safety and alignment need a very high bar.
- Pushback (basedjensen): the cited paper is a thought experiment with no real-world examples; no physical way to cycle CPU temps fast enough to transfer meaningful data, and no onboard sensors with enough resolution. "Stop inventing sci-fi stories for safety reasons."
- The exchange captures the tension between frontier-lab safety framing and engineering skepticism about extreme risk scenarios.
More from AGI Musings
- Databases to distributed systems: every systems skill is merging into AI inference and hardware — Abhishekcur · 2026-11-02
- Limitless analogy: smarter people may gain far more from superintelligence — McDonaghMatthew · 2026-11-02
- Hunting for the most concrete "curing cancer with AI" roadmap of 2025 — iskander · 2026-11-02
- Avoiding AI brain rot: Miles Cranmer's lecture on learning with AI — _ScottCondron · 2026-11-02
- Yacine mocks "autonomous research" hype as Naam argues RSI loop needs 5-10x boost to run away — yacineMTB · 2026-11-02
- Vitalik's "post-AI cryptography": pseudonyms are dead, per-action anonymity is in — devanshmehta · 2026-11-02