Last week, MIT CSAIL published Sparks of Weight-Space Programming. Given the raw weights of a small network, GPT-6 Astra could tell which game it had been …
Alex Krentsel on Twitter / X
i've reproduced the results from the MIT blog post today on weight-space programming. but one additional result i have to add: this is a new, step-change emerging capability that's appeared in just the latest set of models. pic.twitter.com/EhMsQaaOkL— Alex Krentsel (@AlexKrentsel) November 2, 2026
Rikiya Takehi on Twitter / X
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:… pic.twitter.com/DwTwzXzSbE— Rikiya Takehi (@rikiyatakehi) November 2, 2026
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, using a variety of recent tools and algorithms or even via direct weight editing.
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, using a variety of recent tools and algorithms or even via direct weight editing.
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
Qwen 3.8 27B on my laptop can interpret model weights, too
Yesterday’s hot paper was Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights by Rikiya Takehi, Jayden Teoh, Alex Zhang, and Omar Khattab. The paper found …
GPT-6 AstraでQwen3.5-0.8Bの重みを直接編集、数学スコアは約6倍に
「GPT-6 Astra」を使って「Qwen3.5-0.8B」の重みを直接書き換えると、数学の性能が最大6倍に向上する。武樋力哉氏らマサチューセッツ工科大学の研究チームは11月2日、「重み空間プログラミング」(Weight-Space Programming)と呼ばれる手法に関する研究結果を公開した。
gpt-oss:120b
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
gpt-oss:20b
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
How Open Weights Are Changing the AI Race | Serverless Guru
Open Weight models: what they are, why you should care, and how the work of the open-source fine-tuning community around those models is reshaping daily life, both for developers and for everyday AI users.
Open-weight AI is having its Kubernetes moment. Let's not ruin it. | Tobi Knaup
Open-weight models are becoming the foundation for the next AI ecosystem. The US should compete in it, not wall itself off.
Y Combinator's Garry Tan wants US open-weight AI labs to 'distill' frontier models, too | TechCrunch
Tan wants smaller, American open-weight AI labs to use the same kind of training techniques on American frontier AI labs, giving the U.S. a more robust set of open-weight options that aren’t Chinese.
Multi-Stage Programming: Its Theory and Applications | Guide books
The OpenAI Open weight model might be 120B
726 votes, 163 comments. The person who "leaked" this model is from the openai (HF) organization So as expected, it's not gonna be something you can…
AI weight-space programming
Qwen 3.8 27B on my laptop can interpret model weights, too
The 'Astra can read and write weights to improve Qwen' post is misleading · honnibal.dev
Rikiya Takehi on Twitter / X
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
Alex Krentsel on Twitter / X