Skip to content
Xinzhiyuan · WeChat

Top AI wrote dozens of pages of derivation before reviewers found the problem was wrong

顶级AI撞上低级乌龙:连写几十页推导,结果发现题干错了?

Xinzhiyuan says Google DeepMind used Aletheia on 700 Erdős problems and got 13 original answers. The pipeline had Gemini Deep Think produce 200 candidates, then a verifier reduced them to 63. The post says Erdős-75 had a wrong premise, yet Aletheia wrote dozens of proof pages.

Why it matters: DeepMind's Aletheia pipeline ran Gemini Deep Think on 700 Erdős problems, and Erdős-75, whose statement is itself wrong, still produced dozens of pages, showing where automated verification breaks down.

Read the original ↗Export Markdown