---
title: weight space programming
url: "https://goremy.ai/blog/tag/weight-space-programming"
type: keyword
updated: "2026-11-07T06:20:09.620Z"
posts: 4
---

# weight space programming

Posts about weight space programming (4).

## Posts (4)

- [How to Run the Edited Qwen3.5 0.8B Locally With vLLM](https://goremy.ai/blog/articles/run-weight-edited-qwen3-5-0-8b-vllm) (2026-11-07): Serve Hugging Face's rebuilt weight-edited Qwen3.5 0.8B beside the original in vLLM and compare looping on a 2^100 mod 7 prompt and MATH-500 problems.
- [What Is Weight Space Programming? MIT's GPT-6 Astra Paper](https://goremy.ai/blog/articles/weight-space-programming-mit-gpt-6-astra) (2026-11-06): MIT's Sparks of Weight Space Programming paper has GPT-6 Astra read and edit another model's weights, lifting a small Qwen's math from 7.9% to 48.1%.
- [Did GPT-6 Astra Really Make Qwen 6x Better at Math?](https://goremy.ai/blog/articles/gpt-6-astra-weight-space-programming-qwen-math) (2026-11-06): An MIT-linked paper says GPT-6 Astra edited 0.016% of Qwen3.5-0.8B's weights for a sixfold math gain. Here is what changed and what to doubt.
- [What Did GPT-6 Astra Do With Raw Model Weights? Results](https://goremy.ai/blog/articles/gpt-6-astra-weight-editing-experiments-results) (2026-11-05): Astra identified games from raw weights, fixed a stuck car by editing 3.5% of a network, and wrote Atari networks from scratch. Here are the numbers and limits.