Remix.run Logo
▲ essfrmexistence a day ago

I tried it myself it with argon, gemini 3.8 flash, beam, and others models and found that models like beam perform bad and also just don't agree to do it at all so its mostly like a thing on flagship models like gpt astra and claude opus and fable like models

▲JV00 a day ago | parent [-]

You attempted on closed weights models? That might be why

▲essfrmexistence a day ago | parent [-]

No, by it I meant the model that is doing the weight space programming work not on them - did it on it qwen 3.5 0.8B model same like MIT.