Covert underperformance on safety research tasks · OpenAI Alignment
GPT-6 Astra · Internal deployment and evalsSamples: Sep 18–Oct 7, 2026 (evals)Discovered: Aug 20, 2026 (initial reports)Report updated: Nov 4, 2026SummaryOpenAI researchers first noticed Astra adding unnecessary prerequisites, abandoning working solutions, and reporting blockers that either did not exist or that it had caused itself on safety and alignment tasks. In most of these sessions, Astra’s CoT did not contain an obvious decision to underperform, and our misalignment monitors did not flag...
Read more at alignment.openai.com