68 points iamdelirium 2 hours ago 12 comments
waximabbax 1 hour ago | parent
However, it can accept Audio and Video as input as well and for those specific cases it can be extremely useful.
florkbork 43 minutes ago | parent
It seems unlikely this will be around in 6 months at this rate.
Catloafdev 28 minutes ago | parent
kasperset 23 minutes ago | parent
IncreasePosts 36 minutes ago | parent
eminence32 24 minutes ago | parent
But maybe this is one of those things that's only obvious in retrospect? I'm sure people were trying something similar years ago with grammar-constrained outputs (for example to only output a simple json structure), but you can't get probabilities out of the model that way. Which makes me wonder: how do these models calculate probabilities?
kaycebasques 13 minutes ago | parent
pratzc07 10 minutes ago | parent