News for hackers. Stuff that matters.
Re:OpenAI O3-Mini by WhitneyLand on Tuesday February 04, 2025 @01:21PM (#42936450)
The point is there has to be meaning for reasoning. I think the claim in this paper is very clear and the results are shown decisively.

Research papers relating to reasoning approach and define it in many ways but crucially, the good ones offer a testable claim.

Simply saying “models can’t reason” is ambiguous to the point of being unanswerable.

There are no comments on this comment yet.