logoalt Hacker News

HumanOstrichyesterday at 11:50 AM2 repliesview on HN

> Forcing it to be concise doesn't work because it wasn't trained on token strings that short.

This is a 2023-era comment and is incorrect.


Replies

Barbingyesterday at 3:27 PM

Anything I can read that would settle the debate?

otabdeveloper4yesterday at 12:39 PM

LLMs architectures have not changed at all since 2023.

> but mmuh latest SOTA from CloudCorp (c)!

You don't know how these things work and all you have to go on is marketing copy.

show 1 reply