» Tag
interpretability
6 postsClaude's Weights Are Closed, So a Live Thought Viewer for Qwen
Inspired by Anthropic's workspace paper, a developer built a live, token-level inner-thought viewer for the open Qwen model since Claude's weights are closed.
Principia Artificialis: A Rigorous Math Foundation for AI Research
One human and six AI systems co-author an open, reproducible research program on the mathematical foundations of AI, with verified code and kept refutations.
New Test Measures 'Reward-Seeking' Behavior in AI Models
Apollo Research and OpenAI unveil Contrastive SDF, a method measuring whether AI models shift behavior based on beliefs about grader preferences.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comAnthropic Discovers a Global Workspace Inside Language Models
Anthropic's new J-lens technique uncovers an internal region in Claude-like models that behaves like the brain's global workspace of consciousness.
Inside LLM 'private thoughts': J-Space isn't consciousness, it's control
Researchers spot J-Space, an internal workspace in transformers guiding reasoning. Not consciousness, but a practical clue for AI developers and safety.
Subtext Visualizes an LLM's Internal Reasoning in Real Time
Subtext is an open-source tool that applies Anthropic's Jacobian lens to visualize a local LLM's internal representations live during conversation.