Astra 直接改写 Qwen 权重：数学提升约 6 倍、指令跟随三倍

Token Gremlin @TokenGremlin原推发布于 2026.11.03

在 X 上打开原推

THIS IS A HISTORIC MOMENT. GPT-6 Astra just reached inside another AI and rewired it by hand. No gradients, no training, just direct edits to 0.016% of Qwen3.5-0.8B's weights. The result: its reasoning loops are gone, its math jumped up to 6x and its instruction following tripled. AI is starting to fix other AIs from the inside.

这条是引用着另一条写的：「让 GPT-6 Astra 直接改权重：权重空间编程」