Loading...

Tag trends are in beta. Feedback? Thoughts? Email me at [email protected]

Claude Opus 5.5

Claude Sonnet 5.5

Anthropic: The Situation Report

Yes, Claude can do nine loops

GLM-5.3 and the spread of advanced cyber capabilities

Sonnet 5.5

Claude discovers a novel enzyme system with CRISPR-like repeats

What will our economic future look like?

Formalizing Fermat's Last Theorem

Partnering with Accenture on Embedded Evaluation

Detecting and countering misuse of AI: September 2026

Claude Fable 5.1 and Claude Mythos 5.1

Improving our alignment and security efforts

How Claude's text watermarking works

Patterns and problems in emerging multi-agent systems

Putting money where their mouth is: Anthropic’s Claude autonomously designs disease-targeting proteins with real wet-lab proof, hitting a 35% success rate vs 10–15% human average

Previewing the Model Hardware Standard

Learning more about Claude's mathematical capabilities

Anthropic Risk August 2026 [pdf]

The Conceptual Reasoning Index

Claude Opus 5

Societal Impacts: Claude's values across models and languages

Discovering Cryptographic Weaknesses with Claude

Investigating three real-world incidents in our cybersecurity evaluations

Claude Opus 5

Our position on open-weights models

Redeploying Fable 5

A new way to reflect on how you use Claude

Ben Bernanke Joins Anthropic Oversight Trust

Anthropic updates their terms to verify age or identity

More →