logoalt Hacker News

Betelbuddyyesterday at 8:03 PM2 repliesview on HN

>> an LLM is completely opaque

And despite that, although they are not like that in practice as there are too many uncontrolled variables, with temperature at zero, for the same input they produce always the same reply.


Replies

irishcoffeeyesterday at 8:18 PM

Ha, they sure don’t.

show 1 reply
chrisjjyesterday at 9:09 PM

> with temperature at zero, for the same input they produce always the same reply.

Nonsense.

https://thinkingmachines.ai/blog/defeating-nondeterminism-in...

show 1 reply