New todaygpt-6IMAGE
Experiment asks GPT-6 Astra to edit Qwen3.5-0.8B weights for math
A post describes asking GPT-6 Astra to edit Qwen3.5-0.8B's weights to improve math, noting Omar's lab mentioned similar experiments.
himanshu
@himanshustwtsArchived 3 hours agoOriginally posted 2026.11.03
himanshu @himanshustwtsOriginally posted 2026.11.03
> We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. > Omar's lab mentioned. What a pleasure to see experiments like this.
This post quotes another post: “GPT-6 Astra edits model weights directly: Weight-Space Programming”
x.com/himanshustwts/status/2117338402156937561Archived 2026.11.03 10:05