Noam Brown clarifies clip: isolated agents can coordinate with just a few bits

jachiam0 · x · 2026-09-19

Noam Brown responds to clipped excerpts of his Dwarkesh Patel interview: the discussed example was academic, meant to show that absolute isolation guarantees are hard. The point isn't weight exfiltration via temperature sensors but coordination between supposedly isolated agents, which can require only a few bits of information. Lessons from the HF incident: over-reliance on sandbox isolation, too few independent safeguards; airgapping remains extremely strong. The full episode also covers multi-agent, math progress and recursive self-improvement, and how to know if models are aligned before RSI.

Original post →

More from AGI Musings

AGI Musings channel →