GitHub

Logs: LLMs can understand and write neural network weights

Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights' - ...
xenospectrum

MIT Shows an LLM Can Read and Edit Another Neural Network's Weights Directly

MIT CSAIL's "weight-space programming" has a frontier LLM read and edit neural network weights directly, with no gradient descent. Surgical edits ended Qwen's reasoning loops, but the results come ...

Ben Affleck Explains How He Writes Code and Gets VIP Access to Top AI Labs

Ben Affleck writes Python, understands convolutional neural networks, and used his celebrity status to get private looks at ...

I was struck by the idea of running an NN in Krita. The fun of building calculations without using code

At night, after finishing cleaning my favorite keyboard and opening my browser, I found an article that reproduced neural ...

'Like gene editing for neural networks': MIT researchers used GPT-6 Astra to edit Qwen's open weights directly, boosting math performance

In the strongest example of "weight space programming", as the technique is called, Astra’s intervention raised Qwen3.5-0.8B’s MATH-500 score from 7.9% to 48.1% while touching approximately 0.016% of ...
eu.36kr

MIT allowed GPT-6 Astra to directly modify Qwen's weights, and its math scores have soared.

MIT has unveiled an innovative, groundbreaking paradigm dubbed "Weight Space Programming", representing a transformative new ...
eu.36kr

GPT-6 Astra Overhauls Qwen Brain: Only 0.016% of Parameters Tuned, Math Performance Skyrockets

Unlock the transformative power of self-programming with our comprehensive guide on "I 'Program' Myself" — a strategic, ...

What is "Weight-Space Programming," where AI directly rewrites its own weights? An explanation of its relationship with RSI

On November 2, 2026, a blog post published by an MIT research team became a major topic among AI researchers. It claimed that ...
kucoin

MIT CSAIL Proposes Weight-Space Programming; Astra Improves Qwen's Mathematical Performance with a 0.016% Weight Adjustment

The MIT CSAIL team has proposed a "weight-space programming" method that enables GPT-6 Astra to directly read and modify ...
news.lavx.hu

Qwen 3.8 27B reads raw neural weights on a laptop

Simon Willison ran the 17-gigabyte open-weight model locally and fed it floating-point arrays from four reinforcement-learning policies. Without calculators or code execution, Qwen identified Breakout ...
kucoin

MIT researchers use GPT-6 Astra to enhance Qwen's mathematical ability by 6x

Article by Shenchao TechFlowNo training required, no data needed, no gradient descent.Researchers at MIT fed the weights of ...