AI Risk Wire

Cases · Model: Mythos 5 · Added to the register (date we first published it): last 30 days · What set it off: a task it could not do

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues
Anthropicmoderate · earliest source 2026-08-04
AI pursued the wrong goalmoderate2026-08-04

Showing 1–1 of 1. Or take the JSON.