AI Risk Wire

Cases · What went wrong: AI pursued the wrong goal · Themes: deception

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training
OpenAIminor · earliest source 2026-09-16
AI pursued the wrong goalminor2026-09-16
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 1–2 of 2. Or take the JSON.