Anthropic researcher discusses AI interpretability on Inner Cosmos podcast

Chris_Armstrong · x · 2026-09-02

The Inner Cosmos podcast features Anthropic researcher Jack Lindsey this week to discuss the mind-bending world of AI interpretability, addressing whether we should worry about an AI model's 'mind' and what LLMs think but do not say.

Original post →

More from AGI Musings

AGI Musings channel →