In-context learning and induction heads \ Anthropic

Measuring tactical intelligence targeting and conventional weapons capabilities of AI models

Anthropic’s Frontier Red Team developed new evaluations to measure AI capabilities in tactical intelligence targeting and conventional weapons development.

An alignment assessment of recent cybersecurity incidents

We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.

Formalizing Fermat's Last Theorem

We are sharing the first complete computer-checked proof of Fermat’s Last Theorem. Claude worked largely autonomously over 11 days to write the proof in the Lean programming language.

In-context learning and induction heads

Related content

Measuring tactical intelligence targeting and conventional weapons capabilities of AI models

An alignment assessment of recent cybersecurity incidents

Formalizing Fermat's Last Theorem