Can a Linear Program Do Weight-Space Programming?

Re:Can a Linear Program Do Weight-Space Programming? by yunruse on Wednesday November 11, 2026 @09:25AM (#50453818)

It's easy to trace that a bit sets a character in a file with absolute certainty; weights are in a highly dimensional space however, so even if ⍺v is good for one test it could easily regress for another.

I suppose the argument is that "editing weights" seems to imply a complex awareness of what each weight means, which is material for AGI hype. Really it's just doing very broad statistics, which is of course interesting but hardly unexpected.

[ Parent | on HN ]

Re:Can a Linear Program Do Weight-Space Programming? by yatopifo on Wednesday November 11, 2026 @10:33AM (#50454629)

I look at it at a slightly different angle. AGI implies broad capabilities including self-improvement without using another AGI. Being able to perform a “surgical procedure” on weights is a clear step in that direction. Direct weight interpretation may work if small model weights are included as training tokens but i doubt it’s useful for self-editing. On the other hand, using simple tools to interpret and edit it’s own weights might work.

[ Parent | on HN ]

Re:Can a Linear Program Do Weight-Space Programming? by FrustratedMonky on Wednesday November 11, 2026 @11:15AM (#50455102)

Yes, the arguments in this thread seem to be around interpreting the word "editing". Is something consciously "editing" by tweaking the correct neurons/weight. Or is it just some linear algebra.

Though, even on re-read, it sure seems like Astra was making some decisions, otherwise what is this saying, that Astra knew how to download some linear algebra tools?

[ Parent | on HN ]