Comment on OK. I'm at wit's end attempting to convince Google's LLM to pronounce an English name correctly.
TehPers@beehaw.org 20 hours agoThe modeld themselves are nondeterministic. Also, they tend to include a hidden (or sometimes visible) random seed that gets input into the models as well.
Powderhorn@beehaw.org 14 hours ago
How delightful. I mean, I knew there were reasons you don’t get the same results twice, but I’ve not dived into how all this works, as it seems to be complete bullshit. But it’s nice to hear that’s a feature.