logoalt Hacker News

hakuninyesterday at 4:54 PM2 repliesview on HN

It helps, but it doesn't make it deterministic. LLMs could all be misled together. A different story would be if we had deterministic models, where the exact same input always results in the exact same output. I'm not sure why we don't try this tbh.


Replies

verdvermyesterday at 5:00 PM

I've been wondering if there are better random seeds, like how there are people who hunt for good seeds in Minecraft

exe34yesterday at 5:06 PM

it's literally just setting T=0. except they are not as creative then. they don't explore alternative ideas from the mean.

show 1 reply