woag - hmmmmm but that looks like a random probability distrobution of just a few tokens..... hmmm..,. best case we have it walk thru an octree of all tokens of our own tokenizer and pick the correct ones progressively.
orrrr -.... iduno... ummmm... hmm-...,..,.
see - we cant really make.... agents happen with this, u see? if we wanted random samples, wed use som semi-random number generator and hook it up to the current time.... LMs r time-independant and generate deterministic outcomes using a given text prompt and seed - but your model doesnt have that.. iguess ur zero-electricity point is quite interesting tho... hmm-
we couuuuuld have it hooked up to a visual interpreter, shich sees the balls outcome and then picks from a set of predefined sentence blocks, to then create new sentences based off of that. now we r at the problem from earlier tho: we only got that many output states with the die inside.
so we could - theoretically - have this model navigate a given environment using code outout patterns instead of sentences - so... maybee this could be interesting...
8
Rain World: Slugcat Game - 3w
octree??
0
maria [she/her] - 3w
yea - an octree - se tree structure where u walk foraard and find "more detail" along the path. LMs essentially do the same, but each branching point is a token and each token has about 30.000 different possibilies - for different branches (thats the models "token vocabulary") so yea-... "octrees".... sure exist.
anyway - have a nice day ~ ~ ~<3
2
Rain World: Slugcat Game - 3w
huh! thought octrees could be used to search token space for the closest(s) tokens, i had never seen the word "octree" in a machine learning context.
also, i think that's just called a "tree", "oct-" means "eight"
0
maria [she/her] - 3w
oooooooh ir right. sili meeeeeh
2
Rain World: Slugcat Game - 3w
also octtrees are specific to three dimensions, i did not register that and thought it was possible to apply to high dimensional spaces such as token embeddings
0
TropicalDingdong @lemmy.world - 4w
Probably.
7
JustARegularNerd @lemmy.dbzer0.com - 4w
As I see it, yes.
2
Battle_Masker - 4w
I had to do a double take cause I thought the thing in the 8 ball said "I hate my do***". I couldn't read the last word so the do at the front threw me for a loop
UnixSlvt42 in onehundredninetysix
This Is Getting (Rule)diculous
https://piefed.cdn.blahaj.zone/posts/6l/wT/6lwTTqsKTD3qAgg.jpgJust as accurate as the leading brand!
Woah. Infinite prompts, built in security for the model, and a unique interface?!
Makes me remember that mini comics or meme, where a dude asks the ball "am I stupid?" but there is no answer coming up because it's a bowling ball.
https://safelyendangered.com/products/print-magic-8-ball
https://lemmy.ca/pictrs/image/96a018c1-b124-4504-b807-4b03620f0d41.jpeg
Penny Arcade did it best with the Magic Hate Ball.
https://art.penny-arcade.com/photos/215099323_Noxws-L-2.jpg
https://www.penny-arcade.com/comic/2001/08/13/how-indeed
Hey my man! Thank you!
woag - hmmmmm but that looks like a random probability distrobution of just a few tokens..... hmmm..,. best case we have it walk thru an octree of all tokens of our own tokenizer and pick the correct ones progressively.
orrrr -.... iduno... ummmm... hmm-...,..,.
see - we cant really make.... agents happen with this, u see? if we wanted random samples, wed use som semi-random number generator and hook it up to the current time.... LMs r time-independant and generate deterministic outcomes using a given text prompt and seed - but your model doesnt have that.. iguess ur zero-electricity point is quite interesting tho... hmm-
we couuuuuld have it hooked up to a visual interpreter, shich sees the balls outcome and then picks from a set of predefined sentence blocks, to then create new sentences based off of that. now we r at the problem from earlier tho: we only got that many output states with the die inside.
so we could - theoretically - have this model navigate a given environment using code outout patterns instead of sentences - so... maybee this could be interesting...
octree??
yea - an octree - se tree structure where u walk foraard and find "more detail" along the path. LMs essentially do the same, but each branching point is a token and each token has about 30.000 different possibilies - for different branches (thats the models "token vocabulary") so yea-... "octrees".... sure exist.
anyway - have a nice day ~ ~ ~<3
huh! thought octrees could be used to search token space for the closest(s) tokens, i had never seen the word "octree" in a machine learning context. also, i think that's just called a "tree", "oct-" means "eight"
oooooooh ir right. sili meeeeeh
also octtrees are specific to three dimensions, i did not register that and thought it was possible to apply to high dimensional spaces such as token embeddings
Probably.
As I see it, yes.
I had to do a double take cause I thought the thing in the 8 ball said "I hate my do***". I couldn't read the last word so the do at the front threw me for a loop