2026-11-02 · America/Los_Angeles · 社区动态 · #1

We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.

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: https://t.co/DwTwzXzSbE

热度 63.4 / 100；排名与评分保留该期记录。