Remix.run Logo
▲ simonw 6 hours ago

No, that was this one - https://rikiyat.github.io/blog/weight-space-programming/ - different authors, different approach.

▲vlovich123 6 hours ago | parent [-]

IIUC the dominant mechanism behind the math improvement remains fixing reasoning loops same as in the previous paper and probably why they picked Qwen3 here. It’s unclear this approach actually scales in any way.