DevOps

J-space in practice: using Anthropic's Jacobian lens to decide what an LLM can forget

Anthropic published Verbalizable Representations Form a Global Workspace in Language Models on July 6, and the vocabulary it introduced is suddenly…

Beyond Reconstruction: Verifying Model Explanations with RECAP

What Changed For years, the field of mechanistic interpretability has relied heavily on natural-language autoencoders to translate hidden model acti…

The safety switch that doesn't actually work

Sparse autoencoders — the core tool of mechanistic interpretability — can identify and amplify specific concepts inside a neural network, but they c…

Mechanistic Interpretability is a 2026 Breakthrough Technology. Here's What That Means for the "LLMs Are Just Matrix Multiplication" Debate

Today a friend of mine — let's leave him nameless — said the line I've been hearing since 2022: "It's still just matrices multiplying, guessing the…