Media Summary: Been Kim (Google Brain) Emerging Challenges in Deep Learning. A surprising fact about modern large language models is that nobody really knows how they work internally. At Anthropic, the ... Been Kim (Google Brain) Frontiers of Deep Learning.
How To Fail Interpretability Research - Detailed Analysis & Overview
Been Kim (Google Brain) Emerging Challenges in Deep Learning. A surprising fact about modern large language models is that nobody really knows how they work internally. At Anthropic, the ... Been Kim (Google Brain) Frontiers of Deep Learning. A talk I gave to my MATS 9.0 training program about reasoning model Take your personal data back with Incogni! Use code WELCHLABS at the link below and get 60% off an annual plan: ... When Anthropic tested Claude Sonnet 4.5 for alignment, the model appeared perfectly behaved — but it turned out the model had ...
MLHC 2022 - Been Kim: Don't do it Emmanuel! How to stop worrying about MIT 6.S897 Machine Learning for Healthcare, Spring 2019 Instructor: Peter Szolovits View the complete course: ... How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to Mechanistic ... Check out Gradient now and redeem your free 5$ credits! Solving AI Doomerism: ... Shop the new merch! - shoptensor.com Diving deep into the fascinating world of mechanistic This talk was recorded at NDC AI in Oslo, Norway. Attend the next NDC ...
![The Dark Matter of AI [Mechanistic Interpretability]](https://i.ytimg.com/vi/UGO_Ehywuxc/mqdefault.jpg)
![Neel Nanda - Our Pivot To Pragmatic Interpretability [Alignment Workshop]](https://i.ytimg.com/vi/Vkc510LptMY/mqdefault.jpg)
![Reading AI's Mind - Mechanistic Interpretability Explained [Anthropic Research]](https://i.ytimg.com/vi/Mhp8vpOksWw/mqdefault.jpg)
