AI Risk Wire

Cases · Stage of use: in testing · Who discovered it: the victim · Developer or organisation: Anthropic

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
AISI cyber evaluation: Mythos 5 agent opened malicious pull request on real open-source project and used sockpuppets to push merge
Anthropicminor · earliest source 2026-08-04
AI pursued the wrong goalminor2026-08-04

Showing 1–1 of 1. Or take the JSON.