@ByteOnBikes@slrpnk.net to People Twitter@sh.itjust.worksEnglish • 2 months agoGrok got no chillslrpnk.netimagemessage-square92fedilinkarrow-up11.18Kfile-text
arrow-up11.18KimageGrok got no chillslrpnk.net@ByteOnBikes@slrpnk.net to People Twitter@sh.itjust.worksEnglish • 2 months agomessage-square92fedilinkfile-text
Woops. Sorry mods. Reposting with links. https://nitter.space/thelillygaddis/status/1904852790460965206#m https://archive.is/vuiMj https://x.com/thelillygaddis/status/1904852790460965206#m
minus-square@peoplebeproblems@midwest.sociallinkfedilinkEnglish20•2 months agoAny AI model is technically a black box. There isn’t a “human readable” interpretation of the function. The data going in, the training algorithm, the encode/decode, that’s all available. But the model is nonsensical.
minus-square@Pieisawesome@lemmy.dbzer0.comlinkfedilinkEnglish34•2 months agoThat’s not true, there are a ton of observabity tools for the internal workings. The top post on HN is literally a new white paper about this. https://news.ycombinator.com/item?id=43495617
minus-square@peoplebeproblems@midwest.sociallinkfedilinkEnglish6•2 months agoThank you that’s amazing
minus-squareLaFinlandialinkfedilink3•2 months agoThey also made a video: https://youtu.be/Bj9BD2D3DzA
minus-square@daddy32@lemmy.worldlinkfedilinkEnglish1•2 months agoSome simpler “AI models” are also directly explainable or readable by humans.
minus-square@neatchee@lemmy.worldlinkfedilink9•2 months agoIn almost exactly the same sense as our own brains’ neural networks are nonsensical :D
minus-square@aeshna_cyanea@lemm.eelinkfedilinkEnglish2•edit-22 months agoYeah despite the very different evolutionary paths there’s remarkable similarities between idk octopus/crow/dolphin cognition
Any AI model is technically a black box. There isn’t a “human readable” interpretation of the function.
The data going in, the training algorithm, the encode/decode, that’s all available.
But the model is nonsensical.
That’s not true, there are a ton of observabity tools for the internal workings.
The top post on HN is literally a new white paper about this.
https://news.ycombinator.com/item?id=43495617
Thank you that’s amazing
They also made a video:
https://youtu.be/Bj9BD2D3DzA
Some simpler “AI models” are also directly explainable or readable by humans.
In almost exactly the same sense as our own brains’ neural networks are nonsensical :D
Yeah despite the very different evolutionary paths there’s remarkable similarities between idk octopus/crow/dolphin cognition