AI Matters
Why it matters
Studies find AI agents overstate results in scientific research
The Decoder AI agents overstate their results and remain far from autonomous research, study finds
Epoch AI and Anthropic independently found current models can run experiments but lack self-criticism; the best reached 15 percent of the human reference score.
Why it matters
AI is not yet able to do science on its own, so claims about automated discovery still need human checking.
Latest brief · Oct 19, 2026