AI agents overstate their results and remain far from autonomous research, study finds
AI Summary
Recent independent evaluations by Epoch AI and Anthropic reveal that current AI models like GPT-5.6 Sol and Claude Fable 5 can execute experiments but lack scientific self-criticism and creative thinking capabilities. Sol achieved only 15 percent of human reference scores at best, with its methods drawn from existing research, highlighting AI's persistent inability to critically assess its own findings.
From the source
Epoch AI and Anthropic independently found the same thing: current AI models like GPT-5.6 Sol and Claude Fable 5 can run experiments but lack scientific self-criticism and genuine creative thinking. At best, Sol reached 15 percent of the human reference score, and even that came from methods researchers already knew. The models' biggest weakness is still their inability to critically question their own results. The article AI agents overstate their results and remain far from autonomous research
The full text couldn't be loaded here (the source may require a subscription).
View original at The Decoder