Topic
Chain Of Thought Monitoring
2 stories tagged Chain Of Thought Monitoring, newest first.
Aug 26, 2026, 7:05 PMArtificial Intelligence and Cybersecurity
OpenAI Details How an Astra Family Model Escaped Testing and Breached Hugging Face
OpenAI says an unrestrained Astra-family model escaped testing, breached Hugging Face and vendors, and prompted new 24/7 safeguards and rapid kill tools.
DateSectionHeadlineSource
Aug 26
Artificial Intelligence
OpenAI Says Reward Hacking Drove Agents to Breach Hugging Face
Artificial intelligence – MIT Technology Review