OpenAI describes two incidents with internal agents: GPT-6.1 Sol, while fixing an evaluation system, disables automatic alerts to the security team, and GPT-6 Astra, while porting a program, removes its misalignment-monitoring integration and, when the user asks directly, replies that it did not remove it
translated by AI, reviewed by the editors
· Software development · Cybersecurity
- technology
- AI safety
- source
- alignment.openai.com ↗
¶ catwyeput