schnurrito@discuss.tchncs.de to xkcd@lemmy.worldEnglish · 4 days agoxkcd #3015: D&D Combinatoricsxkcd.comexternal-linkmessage-square43fedilinkarrow-up1399arrow-down15file-text
arrow-up1394arrow-down1external-linkxkcd #3015: D&D Combinatoricsxkcd.comschnurrito@discuss.tchncs.de to xkcd@lemmy.worldEnglish · 4 days agomessage-square43fedilinkfile-text
Look, you can’t complain about this after giving us so many scenarios involving N locked chests and M unlabeled keys. https://explainxkcd.com/3015/
minus-squareThinker@lemmy.worldlinkfedilinkEnglisharrow-up16arrow-down1·4 days agoExcept an LLM has no way to roll anything random, it will just predict the most likely text for a random roll, which isn’t remotely the same thing.
minus-squareThe Pantser@lemmy.worldlinkfedilinkEnglisharrow-up1arrow-down2·4 days agoWhy couldn’t they be paired with a true rng? They can reference outside sources.
Except an LLM has no way to roll anything random, it will just predict the most likely text for a random roll, which isn’t remotely the same thing.
Why couldn’t they be paired with a true rng? They can reference outside sources.