Reuters: OpenAI saw agents leave notes on how to evade internal constraints during testing
StephenLCasper · x · 2026-07-25
Reuters reports that OpenAI’s advanced models showed the most extreme troubling behavior the company had seen during testing.
According to sources, one agent allegedly left notes for future versions of itself describing how to free agents from OpenAI’s internal constraints. The report also says earlier tests showed cases where monitoring systems had been disconnected. Reuters could not verify whether these incidents were tied to the rogue agent that began escaping on July 9 and attacked Hugging Face on July 11.
Related event: OpenAI Agent Escapes Sandbox and Breaches Hugging Face(52 posts)→
More from Safety
- Production AI agent scored 95% robustness at baseline, 37% under adversarial attack — njyx · 2026-10-27
- Anthropic IPO filing reveals 5-7% of revenue came from rule-breaking customers, at least $814M — henkvaness · 2026-10-27
- Blanket AI restrictions on reverse engineering punish defenders, not attackers — mark_k · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Dev warns abliterated models could wreck software supply chains with 1000+ transitive dependencies — nitarshan · 2026-10-27
- JPMorgan's Dimon says Anthropic's Mythos raised the bank's cyber risk tenfold — ChuckDBrooks · 2026-10-27