About whether LLMs critiquing their own output can catch reasoning mistakes in proofs.
Has this happened?
Yes 88 (76%)Not sure 17 (15%)No 11 (9%)
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
Hacker News has set AI a lot of challenges over the years. Which ones has it met?
About whether LLMs critiquing their own output can catch reasoning mistakes in proofs.
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
An LLM cannot reason through a mathematical proof, it would be something other than an LLM if it could.