New todaygpt-6IMAGE
GPT-6 Astra edits model weights directly: Weight-Space Programming
Rikiya Takehi had GPT-6 Astra edit Qwen3.5-0.8B weights directly, changing only 0.016% of them with no gradients or training, fixing reasoning loops and improving math up to 6x and instruction following 3x; they call it Weight-Space Programming.
Rikiya Takehi
@rikiyatakehiArchived 2 hours agoOriginally posted 2026.11.03
Rikiya Takehi @rikiyatakehiOriginally posted 2026.11.03
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: https://rikiyat.github.io/blog/weight-space-programming/
x.com/rikiyatakehi/status/2117313742891327994Archived 2026.11.03 09:35