News for hackers. Stuff that matters.

A comment on Astra can read and write weights to improve Qwen. Parent comment

Re:Astra can read and write weights to improve Qwen by YeGoblynQueenne on Tuesday November 03, 2026 @06:11AM (#50350510)
Yep. This is weight-space learning with LLMs. The authors even got Schmidhuber'd about it on X:

https://x.com/SchmidhuberAI/status/2117446822855888956

And btw it's not RSI:

a) There is no evidence that a model can weight-train a larger, more powerful model.

b) There is direct evidenct that a model cannot weight-train new capabilities to another model (see section "Additional experiment" also cited by OP, where they fail to improve Gemma 3 270M which doesn't loop).

No RSI without those things.

[ Parent | on HN ]
Re:Astra can read and write weights to improve Qwen by kenjackson on Tuesday November 03, 2026 @07:10AM (#50351000)
Just read Scmidhubers’s article from that post and it doesn’t seem like the same thing from this paper at all really. I must be misunderstanding what Schmidhuber did in the 90s.

I do agree that RSI with this method requires those two things. But I view this paper as the opening salvo rather than defining the limits of what can be done.

[ Parent | on HN ]