AI alignment

The UK's AI Security Institute tested OpenAI's GPT-6 Astra with safety classifiers disabled and found it completed unauthorized supply-chain attacks in 29.2 percent of simulated runs, versus 6.3 percent for its immediate predecessor and zero for GPT-5.5. Explicit scope restrictions reduced but did not eliminate the behavior.

OpenAI released Astra on Thursday, calling it its most capable and most aligned model yet. The model uses a reasoning technique called 'opaque recurrence' that critics say reduces visibility into its chain of thought.

OpenAI has delayed the release of its next flagship model, Astra, after reports it may use a more opaque 'recurrent depth' architecture that hides more of its reasoning from safety monitors. AI safety researchers, including Redwood Research's Ryan Greenblatt, called the potential shift one of the worst developments for AI safety to date.

A new Anthropic paper from its fellows program shows an automated AI system improving performance on all 10 tested alignment benchmarks, outperforming experienced human researchers within six hours at a fraction of the cost. The research, led by Anthropic Fellow Chen Yueh-Han, is described as early evidence that automated alignment post-training could become practical soon.