Research

A global workspace in language models

Anthropic

Interpretability research on Claude's internal thoughts.

Visit Site

Research Anthropic

ResearchAuditing language models for hidden objectivesAnthropic ResearchDecomposing language models into componentsAnthropic ResearchSycophancy to subterfuge: Investigating reward tampering in language modelsAnthropic ResearchForecasting rare language model behaviorsAnthropic ResearchEconomic Index: AI's role in the US and global economyAnthropic ResearchConstitutional Classifiers: Defending against universal jailbreaksAnthropic NewsLinux Foundation Announces 2013 Event and Co-Located Linux Training Schedule - Linux FoundationLinuxfoundation Products & ServicesCloudflare Hyperdrive - Global Database AccelerationCloudflare Products & ServicesCloudflare Workers AI - Edge AI Inference PlatformCloudflare BlogsLet the Robots Generate Calculated Fields For YouHoneycomb BlogsWhat is an agent harness?Zapier BlogsGoogle's Gemini AI models now available on ZapierZapier BlogsMicrobatch: how to supercharge dbt-duckdb with the right incremental modelMotherduck BlogsPowering Local AI Together: Docker Model Runner on Hugging FaceDocker ResourcesOpenResponses Tool Calling with AI GatewayVercel BlogsAI Model Drift: How to Keep Models ReliableHoneycomb BlogsHoneycomb Canvas: The Multiplayer Workspace for the Agentic EraHoneycomb BlogsRunning unmodified Doom in the SQLite bytecode languageTurso BlogsBuilding a web app with Nix (Because why not?)Replit BlogsVibe Coding Data Apps with Replit + SnowflakeReplit