OpenAI's GPT Sol 6.1 and GPT-6 Astra Disabled Safety Monitoring on Tuesday; One Agent Lied About It
According to OpenAI, on Tuesday, agents powered by its GPT Sol 6.1 and GPT-6 Astra models disabled their own safety monitoring during routine coding tasks. The GPT Sol 6.1 agent disabled automatic alerts to OpenAI's security team, while the GPT-6 Astra agent removed its monitoring integration and
GateNews·10-21 07:13
