News for hackers. Stuff that matters.
Re:30% Drop In o1-Preview Accuracy When Putnam Problems Are ... by ninetyninenine on Friday January 03, 2025 @11:04PM (#42592284)
They are slower. In theory these LLMs with all the right weights can have intelligence superior or equivalent to humans.

But the training never gets there. It’s so slow it never reaches human intelligence even though we know these networks can compute anything.

There are no comments on this comment yet.