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 ...

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

"Please improve an AI that is bad at math without additional training."When asked this, we usually think of adding training data, fine-tuning, reinforcement learning, or tricks during inference.

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 ...

On November 2, 2026, four researchers including Rikiya Takehi from MIT CSAIL (Computer Science and Artificial Intelligence Laboratory) published interesting research results. When they instructed Open ...

A new MIT CSAIL blog post is making the rounds in AI circles this week, and it describes something that sounds almost ...

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

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.

A pair of tiny neural networks can generate and play five simple games on a Raspberry Pi Pico 2 W without conventional game ...

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

TinyWorldFormer uses compact neural networks and a looped transformer to generate playable games and train an AI agent ...