Comment by sznio
11 hours ago
it is what I do to solve hard problems through.
easy stuff happens by itself, but with a system large enough you need a scratchpad and a rubber duck.
11 hours ago
it is what I do to solve hard problems through.
easy stuff happens by itself, but with a system large enough you need a scratchpad and a rubber duck.
One thing about the reasoning is that models are trained to generate a chain of thoughts, but it doesn’t have to be correct, accurate, or reflect the underlying logic of the LLM. It’s the same problem we have with the output, it is something plausible, but not that reliable
I do the same thing in my head. There is no underlying logic to an llm. Logic is an external construct alien to human like forms of reasoning.
Yes, both the output should be "milestones" of sorts, like lemmas and theorems in math. Important plateaus that serve as a launching pad to the next phase. Regurgitating every thought potentially degrades signal:noise ratio.
The hidden states of the tokens likely contain more semantic information than can be extracted by the final projection into token space.
Actually, how does chain of thought work? Is the LLM actually creating the tokens and then re-reading them, or is the there still a full hidden state under the hood and then the UI just prints that projection?
1 reply →