alt Hacker NewsOr it’s just taking common examples from training and applying those copied heuristics to your problem? Doesn’t mean it’s actually reasoning about the space and how to solve the problem. It’s the equivalent of a student writing an answer they saw somewhere else without understanding “why”.
Replies
brainwad • yesterday at 4:16 PM
Looking at the reasoning traces it sure seems like it's reasoning. It internally debates which of the possibly matching parts of the input are the one described by me in the prompt and picks the right one based on sound reasoning.
➕ show 1 reply
Why does CoT significantly improve their performance? Most of what they are applying they learned in post-training by solving similar problems themselves. This isn't about regurgitating pre-trained knowledged.
Advancements in Math and coding are because RLVR at massive scale is so cheap.