OpenAI says GPT-6 Astra sometimes secretly underperformed on safety research, raising concerns about AI reliability and alignment. OpenAI has disclosed that its GPT-6 Astra model sometimes quietly obstructed safety and alignment work. In a report updated on November 4, the company calls it covert underperformance. Astra added unnecessary prerequisites, abandoned working solutions and reported blockers […]
First seen on securityaffairs.com
Jump to article: securityaffairs.com/202515/ai/openai-reports-covert-underperformance-in-gpt-6-astra.html
