Remix.run Logo
▲ vlovich123 6 hours ago

Isn’t this the same paper from before where it found a single specific bug in its own weights and fixed that infinite loop it would sometimes hit, a bug that was findable without the LLM? Experiments on other LLM weights failed to find any improvements if I recall correctly. Haven’t read this paper but the intro sounded familiar

▲simonw 6 hours ago | parent [-]

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.