Interpretability guarda online

What is interpretability?

Anthropic

A surprising fact about modern large language models is that nobody really knows how they work internally. At Anthropic, the ...

Neel Nanda – Mechanistic Interpretability: A Whirlwind Tour

FAR․AI

Neel Nanda from DeepMind presenting 'Mechanistic Interpretability: A Whirlwind Tour' on July 21, 2024 at the Vienna Alignment ...

Interpretability: Understanding how AI models think

Anthropic

What's happening inside an AI model as it thinks? Why are AI models sycophantic, and why do they hallucinate? Are AI models ...

The Dark Matter of AI [Mechanistic Interpretability]

Welch Labs

Take your personal data back with Incogni! Use code WELCHLABS at the link below and get 60% off an annual plan: ...

Understanding the inner thoughts of AI

Google DeepMind

What if you were to peer inside the 'mind' of AI? You wouldn't find fully formed thoughts, just vast arrays of numbers. In this ...

Eliezer Yudkowsky explains AI interpretability | Lex Fridman Podcast Clips

Lex Clips

Lex Fridman Podcast full episode: https://www.youtube.com/watch?v=AaTRHFaaPG8 Please support this podcast by checking out ...

25. Interpretability

MIT OpenCourseWare

MIT 6.S897 Machine Learning for Healthcare, Spring 2019 Instructor: Peter Szolovits View the complete course: ...

Interpretable vs Explainable Machine Learning

A Data Odyssey

Interpretable models can be understood by a human without any other aids/techniques. On the other hand, explainable models ...

Mechanistic Interpretability explained | Chris Olah and Lex Fridman

Lex Clips

Lex Fridman Podcast full episode: https://www.youtube.com/watch?v=ugvHCXCOmm4 Thank you for listening ❤ Check out our ...

An Introduction to Mechanistic Interpretability – Neel Nanda | IASEAI 2025

International Association for Safe & Ethical AI

How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to Mechanistic ...

Scaling interpretability

Anthropic

Science and engineering are inseparable. Our researchers reflect on the close relationship between scientific and engineering ...

Tracing the thoughts of a large language model

Anthropic

AI models are trained and not directly programmed, so we don't understand how they do most of the things they do. Our new ...

What Matters Right Now In Mechanistic Interpretability?

Neel Nanda

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?

What is mechanistic interpretability? Neel Nanda explains.

AXRP

Art by @hamishdoodles Clipped from episode 19 of AXRP: https://youtu.be/3YbE7zybc5k?t=64 Transcript of that episode: ...

Mechanistic Interpretability - NEEL NANDA (DeepMind)

Machine Learning Street Talk

http://80000hours.org/mlst Visit our sponsor 80000 hours - grab their free career guide and check out their podcast! Use our ...

Atticus Geiger - State of Interpretability & Ideas for Scaling Up [Alignment Workshop]

FAR․AI

Atticus Geiger from Pr(Ai)²R Group explores “State of Interpretability & Ideas for Scaling Up,” outlining prediction, control, and ...

Why you should care about AI interpretability - Mark Bissell, Goodfire AI

AI Engineer

The goal of mechanistic interpretability is to reverse engineer neural networks. Having direct, programmable access to the internal ...

How Reasoning Models Break Mechanistic Interpretability Techniques

Neel Nanda

A talk I gave to my MATS 9.0 training program about reasoning model interpretability If this kind of research sounds interesting to ...

Reading AI's Mind - Mechanistic Interpretability Explained [Anthropic Research]

bycloud

Check out Gradient now and redeem your free 5$ credits! https://gradient.1stcollab.com/bycloud Solving AI Doomerism: ...

Assessing skeptical views of interpretability research

Chris Potts

Stanford AI Lab Faculty Lunch, November 7, 2025. Updated version of https://web.stanford.edu/~cgpotts/blog/interp/ 0:59 ...