@paul_cal: 50k likes, mostly BS. Worth knowing: recent models can read & write weights in some toy problems without tools. This wi…
Summary
A tweet criticizes a viral claim about 'Weight-Space Programming' where GPT-6 Astra supposedly edits Qwen3.5-0.8B weights to boost math performance, noting the results lack competent baselines and the Qwen result is mere bug fixing, while acknowledging that models reading/writing weights in toy problems is a real trend worth watching.
View Cached Full Text
Cached at: 11/03/26, 02:33 PM
50k likes, mostly BS. Worth knowing: recent models can read & write weights in some toy problems without tools. This will surely accelerate & eventually become important
None of the big claims have competent baselines, & the Qwen result is bug fixing, def not RSI-shaped https://t.co/0EvcqgkQey
Rikiya Takehi (@rikiyatakehi): 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:
Similar Articles
@rikiyatakehi: 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…
A blog post introducing "Weight-Space Programming," where frontier LLM GPT-6 Astra natively reads and edits neural network weights—changing only 0.016% of Qwen3.5-0.8B's weights to boost MATH-500 from 7.9% to 48.1% and tripling IFEval, without gradients or training.
The 'Astra can read and write weights to improve Qwen' post is misleading
A blog post argues that the 'Astra can read and write weights to improve Qwen' claims are misleading, showing the headline Qwen math result actually relies on writing Python code and running the model, not directly reading raw weights as advertised.
@lateinteraction: you thought LLMs can only do text optimization and discovery for prompts, harnesses, and code? turns out they’re starti…
研究提出「Weight-Space Programming」：让 GPT-6 Astra 直接编辑 Qwen3.5-0.8B 的权重，在不使用梯度或训练的情况下仅修改 0.016% 权重，修复推理循环并将数学能力提升至 6 倍、指令遵循提升 3 倍。
@NeelNanda5: This is a cool paper, but I think it's best thought of as Astra is surprisingly capable of doing old school mechanistic…
Neel Nanda comments on a paper where GPT-6 Astra edits Qwen3.5-0.8B weights to improve math, arguing the result shows LLMs are surprisingly good at classic mechanistic interpretability techniques rather than anything fundamentally new.
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
A research blog post finding that frontier LLMs can natively read and write neural network weights — diagnosing trained policies, editing weights to fix reasoning loops and boost Qwen3.5-0.8B's MATH-500 from 7.9% to 48.1%, and hand-writing small game-playing networks — a capability the authors call Weight-Space Programming.