Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in LLMs. Parent comment
Sophisticated folks aren't doing the worlds most simplistic/stupid decoding.
Gotta go beyond LLMs 101 to see what's actually happening. Even in training folks are predicting several tokens ahead.
There are no comments on this comment yet.
Sophisticated folks aren't doing the worlds most simplistic/stupid decoding.
Gotta go beyond LLMs 101 to see what's actually happening. Even in training folks are predicting several tokens ahead.