In-context Learning and Induction Heads

An off switch for dual use knowledge in AI models

A global workspace in language models

New interpretability research reveals an emergent mental workspace in Claude that holds internal thoughts that don’t appear in the model’s output.

Anthropic Economic Index report: Cadences

In our latest Economic Index report, we sample hourly for the first time to ask: When do people come to Claude? What do they produce with it? And how do they perceive AI's impact on their work?