logoalt Hacker News

yorwba • today at 11:08 AM • 1 reply • view on HN

The common definition of "reasoning" for all three is "performing a sequence of intermediate steps with multiple passes through the model before outputting an answer." The main difference is that the reasoning models in TFA and [1] are puzzle-solving models, not language models.


Replies

saithound • today at 12:09 PM

Well, yes, that's the very generous definition of reasoning I was referring to, under which almost any iterative computation could count as reasoning.