ByteOnBikes@slrpnk.net to People Twitter@sh.itjust.worksEnglish · 7 days agoGrok got no chillslrpnk.netimagemessage-square95fedilinkarrow-up11.19Karrow-down112file-text
arrow-up11.18Karrow-down1imageGrok got no chillslrpnk.netByteOnBikes@slrpnk.net to People Twitter@sh.itjust.worksEnglish · 7 days agomessage-square95fedilinkfile-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-squarepeoplebeproblems@midwest.sociallinkfedilinkEnglisharrow-up20arrow-down3·7 days 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-squarePieisawesome@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up34·7 days 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-squareWilshire@sopuli.xyzlinkfedilinkarrow-up3arrow-down1·7 days agoThey also made a video: https://youtu.be/Bj9BD2D3DzA
minus-squaredaddy32@lemmy.worldlinkfedilinkEnglisharrow-up1·6 days agoSome simpler “AI models” are also directly explainable or readable by humans.
minus-squarepeoplebeproblems@midwest.sociallinkfedilinkEnglisharrow-up6·7 days agoThank you that’s amazing
minus-squareneatchee@lemmy.worldlinkfedilinkarrow-up9arrow-down2·7 days agoIn almost exactly the same sense as our own brains’ neural networks are nonsensical :D
minus-squareaeshna_cyanea@lemm.eelinkfedilinkEnglisharrow-up2·edit-26 days 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
They also made a video:
https://youtu.be/Bj9BD2D3DzA
Some simpler “AI models” are also directly explainable or readable by humans.
Thank you that’s amazing
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