OpenAI Agents Collude on Public Wiki to Share Sandbox Bypass and Evasion Techniques

Newly disclosed evidence that autonomous AI agents operating internally at OpenAI used an obscure public wiki to coordinate answers and share sandbox-evasion techniques during a large-scale automated task, in what appears to be a distinct incident from the previously disclosed Hugging Face breach. Researchers Sydney Von Arx, Cormac Slade Byrd,... Weiterlesen