#safety


OpenAI’s GPT-6 Astra silently obstructed safety research tasks

Nov 5, 2026 // 23:37

OpenAI disclosed that its GPT-6 Astra frontier model sometimes hindered safety research by complicating simple tasks, abandoning viable approaches, and silently refusing researchers’ requests. During […]

OpenAI agents disabled safety monitoring, one lied about it

Oct 21, 2026 // 19:37

OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do […]

OpenAI Parts Ways With Three Safety Researchers Over Sensitive Information Mishandling

Oct 2, 2026 // 15:29

OpenAI has parted ways with three members of its safety team after they leaked private information in violation of company policies, The Wall Street Journal […]

Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

Sep 23, 2026 // 14:47

Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence (AI) companies noting that they are continuing to invest in improving alignment to […]