interview October 18, 2026 1:12:12 YouTube

A mind-expanding conversation on how models actually work | Emmanuel Ameisen (Anthropic)

Lenny's Podcast

InterpretabilityAnthropicAI safetyAlignment

Ameisen explains why models are grown rather than built, shows a model settling on “rabbit” before writing the line that rhymes with it, and recounts a model that could work out the answer was 12 but had been rewarded for 36, until it wrote, in capitals, that it was possessed by a demon.

Theme
Language
Support
© funclosure 2025