About whether LLMs that score well on reasoning benchmarks actually understand logic.
Has this happened?
Yes 60 (49%)Not sure 43 (35%)No 19 (16%)
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 that score well on reasoning benchmarks actually understand logic.
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
GPT4o still can't reason. It is super fancy autocomplete.
https://i.imgur.com/z83umbk.jpeg
Here I change a widely known riddle to the opposite answer, and I manage to make it state them both as the answer.