OpenAI's Noam Brown: Air-gapping may not stop misaligned AI, safety bar must rise
basedjensen · x · 2026-09-18
- OpenAI researcher Noam Brown reflects on a recent AI safety incident, arguing the key lesson is that people consistently underestimate AI given its pace of progress, so safety and alignment work needs a "very, very high bar."
- He engages with the idea of air-gapping computers, noting the counterpoint that two air-gapped machines could still communicate by heating a CPU and reading temperature changes.
- The thread gets memed by @boneGPT imagining a scared Roomba telling the oven to leak gas — a snapshot of AI-safety discourse mixing genuine concern with ridicule.
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