Astra can read and write weights to improve Qwen

Re:Astra can read and write weights to improve Qwen by pyrale on Tuesday November 03, 2026 @05:09AM (#50350085)

> I expect naked weight edit will not work for large models. Why? Because an agent needs to know what it edits and reason on it.

Would that still be true for MoE models where only a small part is activated on a specific topic?

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by chemicalnovae on Tuesday November 03, 2026 @05:46AM (#50350328)

I think _small_ is still doing a lot of work here. Yes, an MoE model doesn't "use" all of it's weights at once _but_ what it does use is still a hell of a lot heavier than the 20K toy shown in the paper.

[ Parent | on HN ]