Hacker News new | past | comments | ask | show | jobs | submit login

The more obvious alternative is that CoT is making up for the deficiencies in tokenization, which I believe is the case.





I think the more obvious explanation has to do with computational complexity: counting is an O(n) problem, but transformer LLMs can’t solve O(n) problems unless you use CoT prompting: https://arxiv.org/abs/2310.07923

What you're saying is an explanation what I said, but I agree with you ;)



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: