News for hackers. Stuff that matters.
Re:Chain-of-Thought Reasoning Without Prompting by danielmarkbruce on Saturday February 17, 2024 @04:17PM (#39413636)
Of course they do. Beam search is a thing. The reason it's not used as much as it might seem to make sense - cost. Do a greedy search and you run through the model x times where x is the number of tokens generated. Run top-k at every step, the number of runs through the model gets astronomical quickly.

There are no comments on this comment yet.