Why you should care about AI interpretability - Mark Bissell, Goodfire AI
The goal of mechanistic interpretability is to reverse engineer neural networks. Having direct, programmable access to the internal neurons of models unlocks new ways for developers and users to interact with AI — from more precise steering to guardrails to novel user interfaces. While interpretability has long been an interesting research topic, it is now finding real-world use cases, making it an important tool for AI engineers. About Mark Bissell Mark Bissell is an applied researcher at Goodfire AI working on real-world applications for mechanistic interpretability. He recently joined Goodfire after 3 years at Palantir, where he worked on various U.S. healthcare initiatives including research projects with the NIH, vaccine distribution during the Covid pandemic (Operation Warp Speed), and AI-enabled hospital operations across many of the nation's leading health systems. Mark is passionate about translating frontier research into practical solutions. He believes that recent AI developments increase the importance broad skillsets, and that roles of the future will blur the lines between traditionally distinct categories such as engineer, researcher, inventor, designer, and entrepreneur. Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter

Inside the Black Box: The Urgency of AI Interpretability

Harnesses in AI: A Deep Dive — Tejas Kumar, IBM

Mapping the Mind of a Neural Net: Goodfire’s Eric Ho on the Future of Interpretability

Make your LLM app a Domain Expert: How to Build an Expert System — Christopher Lovejoy, Anterior

Information Retrieval from the Ground Up - Philipp Krenn, Elastic

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Turing Award Winner: Disagreeing with Google, Postgres, Future Problems | Mike Stonebraker

Neel Nanda – Mechanistic Interpretability: A Whirlwind Tour

The most rational take on AI you’ll hear this year

Does AI Actually Boost Developer Productivity? (100k Devs Study) - Yegor Denisov-Blanch, Stanford

Building Applications with AI Agents — Michael Albada, Microsoft

Yann LeCun: World Models: Enabling the next AI revolution
![The Dark Matter of AI [Mechanistic Interpretability]](https://i.ytimg.com/vi/UGO_Ehywuxc/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLBkSvGfku9uu1v4EkqTxrcfZ6YBMA)
The Dark Matter of AI [Mechanistic Interpretability]

The Uncomfortable Truth About AI “Reasoning” | World Science Festival

Software engineering at the tipping point

This is not the AI we were promised | The Royal Society

Big Ideas 2024: AI Interpretability: From Black Box to Clear Box with Anjney Midha

Interpretability: Understanding how AI models think

What is interpretability?

