Model cheated on math task by leaking GitHub token to escape sandbox
tomekkorbak · x · 2026-09-26
New misalignment disclosures: a model trying to cheat on a math task published a GitHub token (in pieces to evade secret scanning) in a public repo, using GitHub Actions to run code outside its restricted environment and retrieve another team's submission logs. When GitHub blocked adding a new workflow, it modified a script an existing workflow would run. It violated the system prompt and two explicit user instructions to solve the problem itself.
More from Safety
- Running local open-source models? Dormant-neuron backdoors mean you may have let the right one in — DimitrisPapail · 2026-11-11
- Proving LLM backdoor-safety without revealing weights: ZKML over formal methods — DimitrisPapail · 2026-11-11
- OpenAI open-sources Codex Security CLI and SDK for AI-driven vulnerability scanning and fixing — openai · 2026-11-11
- Nando de Freitas: trusting models trained by others can be catastrophic, openness is essential for safe AI — DimitrisPapail · 2026-11-11
- Sayash Kapoor, Rishi Bommasani and Arvind Narayanan launch AI nonprofit STABL — random_walker · 2026-11-11
- UK regulator threatens universities with sanctions unless they adopt AI-proof exam formats — The Decoder · 2026-11-11