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.

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 ...

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

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.

"To improve an AI model's intelligence, you have no choice but to prepare massive amounts of data and GPUs, and run ...

"Please improve an AI that is bad at math without additional training."When asked this, we usually think of adding training ...

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 ...

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

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

While the statement "It's not that exaggerated" conveys a casual perception that a certain situation, claim, or phenomenon is ...

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

What happens when one AI tries to fix another? MIT researchers used OpenAI's GPT-6 Astra to modify Alibaba's Qwen AI model directly, boosting its maths scores without retraining it.