tszzl: agentic auto-research makes mechinterp finally reveal what's inside models' minds
tszzl · x · 2026-10-15
Researcher tszzl comments on new mechinterp work: against most experts' predictions, neurons and (MoE) experts turn out to be sensible abstractions that can be studied through ordinary poking and probing — and agentic auto-research made all the difference.
He argues this shows mechanistic interpretability really will reveal what goes on inside models' minds on timeframes that matter: "a great triumph." Caveats: much study and corroboration remains.
More from AGI Musings
- AI-written cold emails hit a wall: Pragmatic Engineer's reply gets templated AI response — marktenenholtz · 2026-10-16
- Ben Bajarin: Enterprise Agentic Adoption Is Infant-Stage, Spend Could Top $1T a Year — BenBajarin · 2026-10-16
- UMD Philosophy hires: junior Philosophy of Mind and joint AI Ethics/Safety positions — sethlazar · 2026-10-16
- Dwarkesh: Anthropic insider expects AI to match humans at AI research within 9 months — ZeroStateReflex · 2026-10-16
- Michigan professor Ben Green: why 'AI for Good' fails and self-regulation won't work — benzevgreen · 2026-10-16
- "Everything Is an Alignment Problem": AI Models, Business Models, Teams, Providers — saranormous · 2026-10-16