← Back to context

Comment by refulgentis

17 hours ago

Is that relevant here? the post discussed writing a long prompt to get a good answer, not issues with ex. step #2 forgetting what was done in step #1.

Yes it is, because the post discussed this approach precisely because unrolling the actual chain of thought in interactive chat does not work.

And it's doubly relevant because chain of thought let's transformers break out of TCO complexity and be UTM. This matters because TC0 is pattern matching while UTM is general intelligence. Forgetting what the model thought breaks this and (ironically) probably forces the model back into one-shot pattern matching. https://arxiv.org/abs/2310.07923