Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> What is less apparent is that humans do.

This seems indeed one obvious hole in the argument of the paper. There is no indication whatsoever that human thinking process is more reliable than LLMs intermediate tokens. Which doesn't make our thinking useless, as messy as it might be. We reorder and explain it after the fact.



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

Search: