phiresky@lemmy.world to Programmer Humor@lemmy.ml · 1 year agoHacking in 1980 vs Hacking in 2024lemmy.worldimagemessage-square115fedilinkarrow-up11.54Karrow-down117cross-posted to: [email protected]
arrow-up11.53Karrow-down1imageHacking in 1980 vs Hacking in 2024lemmy.worldphiresky@lemmy.world to Programmer Humor@lemmy.ml · 1 year agomessage-square115fedilinkcross-posted to: [email protected]
minus-squareStaplesMcGee@lemm.eelinkfedilinkarrow-up12·1 year agoHave the ai not actually know what a bomb is so that I just gives you nonsense instructions?
minus-squareFierySpectre@lemmings.worldlinkfedilinkarrow-up12·1 year agoProblem with that is that taking away even specific parts of the dataset can have a large impact of performance as a whole… Like when they removed NSFW from an image generator dataset and suddenly it sucked at drawing bodies in general
minus-squareRubanski@lemm.eelinkfedilinkarrow-up5·1 year agoSo it learns anatomy from porn but it’s not allowed to draw porn basically?
minus-squarepascal@lemm.eelinkfedilinkarrow-up6·1 year agoBecause porn itself doesn’t exist, it’s a by-product of biomechanics. It’s like asking a bot to draw speed, but all references to aircrafts and racecars have been removed.
Have the ai not actually know what a bomb is so that I just gives you nonsense instructions?
Problem with that is that taking away even specific parts of the dataset can have a large impact of performance as a whole… Like when they removed NSFW from an image generator dataset and suddenly it sucked at drawing bodies in general
So it learns anatomy from porn but it’s not allowed to draw porn basically?
Because porn itself doesn’t exist, it’s a by-product of biomechanics.
It’s like asking a bot to draw speed, but all references to aircrafts and racecars have been removed.
Interesting! Nice comparison