Ex-OpenAI interpretability lead: circuits in trillion-parameter models are mostly legible
gabriel1 · x · 2026-10-16
Nick Cammarata, who co-authored early mechanistic interpretability work at OpenAI and started its first large-scale automated interpretability project, says most neurons and circuits in models up to trillions of parameters are now legible with modern agentic tools — versus 2% legibility with early tools. Adam Majmudar calls it the most important result of the year, moving alignment from "is it even solvable" to "we may solve it within a year" and unlocking recursive self-alignment.
More from AGI Musings
- Beff Jezos declares 'civilizational inflection point' in the acceleration of technological progress — beffjezos · 2026-10-16
- Data scientist: pivoting to AI engineering is the safest career bet for the next 5 years — mdancho84 · 2026-10-16
- AI will be superhuman at science regardless, and Europe can't opt out — teortaxesTex · 2026-10-16
- beffjezos to Aaron Levie: techno-optimism is hyperstitious — basedjensen · 2026-10-16
- AI demos haven't changed since 2023, only gotten better — same scenarios — yangyi · 2026-10-16
- CFR experts: the autonomous weapons debate still has a definition problem — mchorowitz · 2026-10-16