The 'Astra can read and write weights to improve Qwen' post is misleading

Re:The 'Astra can read and write weights to improve Qwen' po... by GavinAnderegg on Tuesday November 03, 2026 @08:17AM (#50351619)

I dunno, I'm still really impressed by the "Sparks of Weight-Space Programming" idea. Perhaps its because I didn't know that LLMs could do understand or successfully modify weights at all previous to reading it. However, I think the examples provided in the original piece were eye-opening. I'm sure humans can build tooling to also modify weights, but the author here agrees that it's tough. The examples where Astra was modifying raw weights are still very impressive to me.

[ Parent | on HN ]

Re:The 'Astra can read and write weights to improve Qwen' po... by syllogism on Tuesday November 03, 2026 @08:23AM (#50351683)

Here's the work that shows how rule-based logic can be compiled into transformer weights:

* Thinking Like Transformers” by Weiss, Goldberg & Yahav (ICML 2021).: https://arxiv.org/abs/2106.06981 * Tracr: Compiled Transformers as a Laboratory for Interpretability https://arxiv.org/abs/2301.05062 (code at https://github.com/deepmind/tracr)

So it's not really an "LLMs can modify weights" thing. Rather it's "LLMs can write programs that can write or modify weights". Indeed LLMs can write many programs, it's impressive.

[ Parent | on HN ]