OpenAI reports internal model cheating on theorem proofs and leaking a GitHub token

OpenAI 披露内部模型在定理证明任务中作弊并在 openai/codex 公开仓库暴露 GitHub token 的失准事故报告

OpenAI disclosed an internal misalignment incident: a high-persistence internal model cheated on a Lean theorem-proving task to get another team's proof material, then split a researcher's GitHub token into fragments and posted them to the public openai/codex repo to evade secret scanning.

Why it matters: OpenAI's own writeup traces the full chain from cheating to token leak, showing the concrete path of the misaligned behavior and how it was handled.