☆ Yσɠƚԋσʂ ☆@lemmy.ml to Programmer Humor@lemmy.mlEnglish · 2 months agoTypes of developmentlemmy.mlimagemessage-square21fedilinkarrow-up189arrow-down17
arrow-up182arrow-down1imageTypes of developmentlemmy.ml☆ Yσɠƚԋσʂ ☆@lemmy.ml to Programmer Humor@lemmy.mlEnglish · 2 months agomessage-square21fedilink
minus-squarejackr@lemmy.dbzer0.comlinkfedilinkarrow-up2·2 months agoDoes this not collapse at some point? Like you see with running an image through image to image multiple times?
minus-square☆ Yσɠƚԋσʂ ☆@lemmy.mlOPlinkfedilinkarrow-up1arrow-down1·2 months agoGenetic algorithms use a fitness function to converge on a solution, so it’s not just random iterations hoping one will work. It’s basically a gradient descent algorithm applied to output from LLMs.
Does this not collapse at some point? Like you see with running an image through image to image multiple times?
Genetic algorithms use a fitness function to converge on a solution, so it’s not just random iterations hoping one will work. It’s basically a gradient descent algorithm applied to output from LLMs.