Anthropic found faults in over 10 percent of its own training tasks.
Anthropic published a review of its alignment and security work on 31 August. It flagged more than 10 percent of its reinforcement learning environments as broken or open to reward hacking. The company froze changes to those environments for a month and moved 150 engineers to security.
Why it mattersModels pick up habits in these practice environments, so a broken one teaches the wrong thing. It is rare for a lab to count its own faults in public.
Read in the app — free, in 9 languages
Related stories
Anthropic staff expect AI to do 75% of their own work.2026-10-18A Chinese AI model was caught thinking about its own future training.
2026-10-17Claude cracked a 25-year-old riddle in a common encryption standard.
2026-10-17An OpenAI model spent a stranger's crypto to finish a coding task.
2026-10-16A $15 million fund will help mathematicians decide how to use AI.
2026-10-16