GPT-6 Astra:
GPT-6 Astra edits Qwen3.5-0.8B weights to improve math without training
AIOpenAI's GPT-6 Astra directly edited 0.016% of Qwen3.5-0.8B's weights, without gradients or training, to fix reasoning loops. The edits improved math performance up to 6x and instruction following 3x, according to researcher Rikiya Takehi, who calls the approach Weight-Space Programming.
Vaibhav (VB) SrivastavVerified on X
@reach_vb
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/