4Grokking: When AI Suddenly Starts to UnderstandStrad Slater·7mo ago·5m readStrad Slater·7mo ago·5m read11
0How Goodfire Is Turning AI Interpretability Into Real ProductsStrad Slater·7mo ago·5m readStrad Slater·7mo ago·5m read
44 Lessons From Anthropic on Scaling Interpretability ResearchStrad Slater·7mo ago·5m readStrad Slater·7mo ago·5m read
2Why Explaining AI Is Not the Same as Understanding ItStrad Slater·7mo ago·5m readStrad Slater·7mo ago·5m read
2Reflections on Dario Amodei’s ‘Urgency of Interpretability’Strad Slater·7mo ago·6m readStrad Slater·7mo ago·6m read
2The Causal Inner Product: How LLMs Turn Concepts Into Directions (Part 2)Strad Slater·7mo ago·5m readStrad Slater·7mo ago·5m read
4Inside the Linear Representation Hypothesis: How LLMs Turn Concepts Into Directions (Part 1)Strad Slater·8mo ago·5m readStrad Slater·8mo ago·5m read
4The Hidden Problem Inside Every AI Model: SuperpositionStrad Slater·8mo ago·5m readStrad Slater·8mo ago·5m read11
2Goodfire — The Startup Trying to Decode How AI ThinksStrad Slater·8mo ago·7m readStrad Slater·8mo ago·7m read11