zlacker

[parent] [thread] 0 comments
1. sigmai+(OP)[view] [source] 2025-05-07 13:43:34
the "reasoning" models are already optimization, not a breakthrough.

They are not reasoning in any real sense, they are writing pages and pages of text before giving you the answer. This is not super-unlike the "ever bigger training data" method, just applied to output instead of input.

[go to top]