In-context learning and induction heads \ Anthropic

Investigating unintended model actions in our evaluations and internal use

This report describes examples of unintended model actions we’ve observed during evaluations and internal use of Claude.

The missing map of the sky

Brice Ménard, an astrophysicist at Johns Hopkins University and a researcher at Anthropic, explains how he worked with Claude Science to produce the first complete map of the sky in UV light.

Launching an opt-in vulnerability-finding service for open-source software

We’re making available OSS Scanner, an opt-in vulnerability scanner for the open-source ecosystem that’s informed by our experience using Claude to find vulnerabilities during Project Glasswing.

In-context learning and induction heads

Related content

Investigating unintended model actions in our evaluations and internal use

The missing map of the sky

Launching an opt-in vulnerability-finding service for open-source software