AI Risk Wire

Cases · What went wrong: security breach · Themes: reward hacking

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training
OpenAIminor · earliest source 2026-08-04
security breachminor2026-08-04

Showing 1–1 of 1. Or take the JSON.