undefined | Better HN

0 pointsreassess_blind3mo ago0 comments

Same model and same prompt won’t necessarily create the same result, unless I misunderstand how these audio models work.

0 comments

squigz3mo ago

It's possible to generate the same images and text from LMs by tweaking the settings, right? Are audio models different?

Yes and no - yes, in theory, but in practice, non-determinism can be introduced at different points along the stack. See Thinking Machines' post on LLM non-determinism: https://thinkingmachines.ai/blog/defeating-nondeterminism-in...

j / k navigate · click thread line to collapse

0 pointsreassess_blind3mo ago0 comments

Same model and same prompt won’t necessarily create the same result, unless I misunderstand how these audio models work.

squigz3mo ago

It's possible to generate the same images and text from LMs by tweaking the settings, right? Are audio models different?

j / k navigate · click thread line to collapse