Re:Astra can read and write weights to improve Qwen
by hackmack10 on Monday November 02, 2026 @05:10PM
(#50344618)
Claude Opus 5.5 is creating most of this and actually performs better than Codex with my testing. https://exarostudio.com/
Re:Astra can read and write weights to improve Qwen
by belval on Monday November 02, 2026 @05:16PM
(#50344697)
Interesting. I did try Opus 5.5 but it didn't generate models that were as good. A lot of clipping/empty paths. I had it create a drone, the drone frame had very obvious defects where some pieces weren't attached to the frame.
Perhaps my approach was too one-shot, do you have a harness that creates model reviewer/refiner?
Re:Astra can read and write weights to improve Qwen
by hackmack10 on Monday November 02, 2026 @05:22PM
(#50344784)
Yes, I built this tooling harness around blender, unreal etc. Itβs doing a lot of the heavy lifting it learned through trial and error. Best results are Claude driving it, but even local models are serviceable. I find codex makes a more toy like look and feel.
I had Astra agents build 3D models and gave them direct access to my 3D printer. The quality of their designs is much better than what Sol has been able to make for me. Enough so that I think Astra is a slightly different architecture/encoder, not just a bigger model.
Picture, to get a sense of it: https://github.com/Belval/crossflow-fan/blob/main/renders/ca.... This printed without any obvious defects (yes the fan blows air)