Skip to main content
PPlamenu
HomeLive feedsPeopleGroupsRulesStaff
Sign in
PPlamenu
HomeLive feedsPeopleGroupsRulesStaff
Sign in
lain@lain@fediffusion.art
⁨4⁩h
https://rikiyat.github.io/blog/weight-space-programming/
rikiyat.github.ioSparks of Weight-Space Programming: LLMs can natively read & write neural network weightsWe find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
⁨Nov⁩ ⁨3⁩, ⁨2026⁩, ⁨04:23⁩
1000
Open original page
BoostsQuotesFavs
also lnkr@lnkr
⁨4⁩h

Replying to @⁨lain@fediffusion.art⁩

@lain just finished reading this and it's kinda nuts. Emergent capabilities my ass, how in the hell would it learn to do that? I wonder if they extensively trained the thing on the, what, binaries of the other weights? jamming it straight through the text tokenizer?

1001
BoostsQuotesFavs
lain@lain@fediffusion.art
⁨2⁩h

Replying to @⁨lnkr⁩

@lnkr yeah it's pretty crazy
0000
Open original page
BoostsQuotesFavs