Ex-OpenAI interpretability lead: models up to trillions of params are mostly legible now
danshipper · 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. His early tools could only decipher 2% of neurons, but with modern agentic tooling, the vast majority of neurons and circuits in models up to trillions of parameters are legible — peeking into AI brains is far easier than thought.
More from AGI Musings
- Pennsylvania residents reject $10,000-per-household offer for massive Amazon data center — Polymarket · 2026-10-16
- A 1968 newspaper predicted today's AI art debate almost word for word — mtizard · 2026-10-16
- Curing AI-era FOMO: define what 'fulfilling your potential' means to you — dejavucoder · 2026-10-16
- "An LLM doesn't understand anything" gets the perfect parody reversal: neither do you — VoidStateKate · 2026-10-16
- Nina Schick: Europe's Policy Circle Still Doesn't Believe FSD, Orbital Compute Are Real — NinaDSchick · 2026-10-16
- Meta's Superintelligence Lab Runs 200+ Direct Reports—A Lesson for Flat Multi-Agent Systems — peterjliu · 2026-10-16