Ex-OpenAI interpretability pioneer: most neurons in trillion-parameter models are now legible
burny_tech · x · 2026-10-16
Nick Cammarata, who co-authored early mechanistic interpretability work at OpenAI, argues interpretability may be the most important scientific problem today. Early tools could only make 2% of neurons legible, leaving him pessimistic — but with modern agentic tooling, the vast majority of neurons and circuits in models up to trillions of parameters are now legible.
More from AGI Musings
- Yudkowsky: interpretability progress is a screwdriver, nowhere near alignment — repligate · 2026-10-16
- Does AI Erode Traditional Family Values? Question Sparks Debate — PierceLilholt · 2026-10-16
- Box CEO Aaron Levie: agent wallets finally make micropayments a good business model — kleffew94 · 2026-10-16
- Surplus incubator offers $100k SAFEs for AI-era for-profit public-good startups in SF — NathanpmYoung · 2026-10-16
- Would you trade a below-average living standard for never working again in an AI economy? — simmol · 2026-10-16
- Yacine: you don't need to live in SF to work on frontier AI — yacineMTB · 2026-10-16