Interpretability Now What

Summary

Been Kim (Google Brain) simons.berkeley.edu/talks/tbd-72 Frontiers of Deep Learning. What's happening inside an AI model as it thinks? Why are AI models sycophantic, and why do they hallucinate? Are AI models ... This is a talk I gave to my MATS 9.0 training scholars about the big picture of mech interp - as of Oct 2025, what had changed? Lex Fridman Podcast full episode: youtube.com/watch?v=ugvHCXCOmm4 Thank you for listening ❤ our ... A surprising fact about modern large language models is that nobody really knows how they work internally. At Anthropic, the ... Art by Clipped from episode 19 of AXRP: youtu.be/3YbE7zybc5k?t=64 Transcript of that episode: ... Quantitative Testing with Concept Activation Vectors (TCAV) Been Kim, Senior Research Scientist, Google Brain Presented at ... How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to Mechanistic ... Neel Nanda (Google DeepMind) discussed his mechanistic Take your personal data back with Incogni! Use code WELCHLABS at the link below and get 60% off an annual plan: ... Recorded 04 September 2026. Terence Tao of the University of California, Los Angeles, presents "Reflections on the Foundations ... Part 1 of a walkthrough of our paper, Progress Measures for Grokking via Mechanistic