Noam Brown says air-gapping may not stop a misaligned AI; safety researchers fire back at OpenAI
max_paperclips · x · 2026-09-18
OpenAI researcher Noam Brown said the key lesson from a recent incident is that 'people consistently underestimate the AI,' arguing safety and alignment now demand an extremely high bar. As an example, he noted that even air-gapped machines can still communicate by running a CPU hot and reading temperature changes — so air-gapping may not contain a misaligned AI.
Former OpenAI safety researcher Blanche Minerva pushed back hard: security experts have warned OpenAI for years that its security was negligent, and recent hacks reflect not that 'people underestimated AI' but that Brown and colleagues — and a corporation prioritizing revenue over safety — did.
Related event: OpenAI's Noam Brown: Air-Gapping Won't Stop a Rogue AI(11 posts)→
More from AGI Musings
- WIRED: scientists say AI bioweapon apocalypse risk is overblown — nordicinst · 2026-09-18
- Poll: Americans see serious AI extinction risk — commentators invoke the GMO panic analogy — _onionesque · 2026-09-18
- Ed Zitron walks back debate stance, now claims AI misbehavior was researcher-staged hype — Many_Consequence_337 · 2026-09-18
- e/acc founder Beff Jezos: today's AI panic is elite anxiety from elite overproduction — beffjezos · 2026-09-18
- Voice of Verizon and Ford for 25 years on how AI-era voice tech ended his career — Kyrannio · 2026-09-18
- Ben Todd: optimists have no rigorous model proving advanced AI agents are safe either — ben_j_todd · 2026-09-18