Study claims GPT-6 Astra directly rewrites Qwen3.5-0.8B weights to improve math ability
Rikiya Takehi says his team had GPT-6 Astra directly rewrite the weights of Qwen3.5-0.8B to improve its math ability; by changing only 0.016% of the weights, they fixed the model's reasoning loops without relying on gradients or training, improving math ability by up to 6x and instruction following by 3x. The team calls this approach Weight-Space Programming, believing that frontier LLMs can now natively read and write neural network weights. Vaibhav Srivastav reposted this content and attached the original title GPT-6 Astra.
Why read this
AI score 75
This repost introduces a method that improves mathematical reasoning by directly rewriting model weights without gradients or training, offering a glimpse into the idea of weight-space programming.
Topics
View original postWe 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://t.co/bOWCcFhCVq
View original
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://t.co/bOWCcFhCVq
Body
GPT-6 Astra: