Goodfire AI’s Bet: Interpretability as the Next Frontier of Model Design — Myra Deng & Mark Bissell

Describes using interpretability methods during training rather than only after, a direction that could change how models are debugged, steered and made safer.

• videoWhy Every Agent needs Open Source Cloud Sandboxes
• videoTerminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders
• video[State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAI
• video⚡️ Reverse Engineering OpenAI's Training Data — Pratyush Maini, Datology

• videoMapping the Mind of a Neural Net: Goodfire’s Eric Ho on the Future of InterpretabilitySequoia Capital
• videoInterpretability: Understanding how AI models thinkAnthropic
• videoGoogle DeepMind's Logan Kilpatrick: Why the Model Eats the HarnessSequoia Capital

Checking sign-in…

Loading comments…