Show HN: Weight-space programming playground with WebGPU A developer released a browser-based WebGPU playground that demonstrates weight-space programming on Qwen3.5-0.8B, letting an LLM inspect the model, edit its weights, evaluate the result and repeat the loop. The walkthrough focuses on a concrete example from experiment 8 of "Sparks of Weight-Space Programming": editing 0.016% of the model's weights to reduce reasoning loops without gradient descent, after the full loop proved to need too much VRAM. I wanted to build a full weight-space programming loop entirely in the browser with WebGPU: let an LLM inspect Qwen3.5-0.8B, edit its weights, evaluate, and repeat. the full loop needed too much VRAM. so I turned it into an interactive walkthrough of a concrete example: editing 0.016% of a model's weights to reduce reasoning loops, no gradient descent. Based on exp8 of “Sparks of Weight-Space Programming.” https://tabbyml.github.io/weight-space-playground/ https://tabbyml.github.io/weight-space-playground/ Previous HN discussion: https://news.ycombinator.com/item?id=50341174 https://news.ycombinator.com/item?id=50341174 Comments URL: https://news.ycombinator.com/item?id=50561436 https://news.ycombinator.com/item?id=50561436 Points: 1 Comments: 0