Princeton study: AI's recursive self-improvement won't come so quickly

Princeton researchers Peter Kirgis and Sayash Kapoor found AI agents can solve AI-research engineering problems but lack the judgment and creativity to produce papers at top machine-learning-conference caliber. They tested agents, including Anthropic's Claude Opus 4.8, with a new 'shadow evaluation' method based on unpublished high-quality papers.

Featured · Peter Kirgis, Sayash Kapoor