Published on December 15, 2025 11:17 PM GMTDiscuss Read More
Introducing Lunette: auditing agents for evals and environments
Published on December 15, 2025 11:17 PM GMTDiscuss Read More
Related Posts
Team Shard: Alignment Mentorship from TurnTrout and Alex Cloud
Published on December 26, 2025 5:20 PM GMTThrough the MATS program, we (Alex Turner and…
Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning
Published on February 6, 2026 7:27 PM GMTTLDR; SAEs can complement and enhance LLM as…
Bridge Thinking and Wall Thinking
There are a couple of frames I find useful when understanding why different people talk…