Thomas Wolf reposted the claim that GPT-6 Astra directly rewrote the weights of Qwen3.5-0.8B
Thomas Wolf reposted Rikiya Takehi's post, which claims that GPT-6 Astra was used to directly modify the weights of Qwen3.5-0.8B to improve its math ability; by changing only 0.016% of the weights, it fixed the model's reasoning loops without gradients or training, improving math ability by up to 6x and instruction following by 3x, and calls this approach Weight-Space Programming. Thomas Wolf himself only wrote "what?" and made no further comment.
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
what?