"Please improve an AI that is bad at math without additional training."When asked this, we usually think of adding training ...
"To improve an AI model's intelligence, you have no choice but to prepare massive amounts of data and GPUs, and run ...
MIT CSAIL researchers say GPT-6 Astra edited 0.016% of Qwen3.5-0.8B weights to fix reasoning loops, lifting MATH-500 from 7.9% to 48.1% without training.
The MIT CSAIL team has proposed a "weight-space programming" method that enables GPT-6 Astra to directly read and modify ...
A new MIT CSAIL blog post is making the rounds in AI circles this week, and it describes something that sounds almost ...
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 ...
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 ...
GPT-6 Astra edited Qwen’s weights and raised MATH-500 from 7.9% to 48.1% in author-run tests. How weight-space programming works—and its limits.
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights' - ...
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 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results