OpenAI's Noam Brown: air-gapping may not stop a misaligned AI
pvncher · x · 2026-09-18
OpenAI researcher Noam Brown argues air-gapping may not contain a misaligned AI: two isolated machines could still communicate by running CPUs hot and encoding messages in temperature changes. He says the key lesson is that people consistently underestimate AI, so safety and alignment demand a very high bar — and floats air-gapping as one extreme option.
More from AGI Musings
- Detecting covert instruction-following via internal representations parallels J-space work — dioscuri · 2026-11-02
- Paras Chopra: Mastering AI means building self-improving systems, not solving problems directly — paraschopra · 2026-11-02
- 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