In this article


An AI made a targeted edit inside another model and helped it deliver more correct answers. Working with a small Qwen model, Astra investigated its behavior, changed a tiny fraction of its internal weights and produced a version that performed substantially better on a separate math evaluation.
The experiment, from researchers at MIT CSAIL, offers a concrete example of AI helping improve AI. They call the approach weight-space programming: using a language model to reason about a network’s weights and change them directly. Research report
The interesting part is what Astra found along the way. Qwen was repeatedly getting caught in long, repetitive responses. A focused change helped it get further with the task it had been given.
How does an edit inside a model become a better answer on the screen?
Two models with different jobs
The model doing the investigating was GPT-6 Astra, called Astra in the research. The model being edited was Qwen3.5-0.8B. Keeping those roles separate makes the experiment easier to follow: Astra proposed and investigated changes; Qwen was the system whose performance was measured.
Astra worked through a controlled Python environment. The researchers’ released logs record its code, the outputs returned to it and the evaluation results, making the investigation available to inspect. Experiment logs
What changing a model actually means
A model’s weights are numerical values used in its calculations. During ordinary training, an optimization procedure repeatedly adjusts those values. Once a trained model is answering a question, its calculations use the weights to turn the supplied context into predictions about what to produce next.
Changing the prompt changes the information entering that process. Changing the weights changes part of the process itself.
For this experiment, Astra could inspect Qwen’s weights, try practice problems and make direct edits. It used feedback from those practice runs to investigate what was going wrong and whether a change helped. The researchers kept the final evaluation questions separate from the questions available during this work. Experiment 8 setup
The process connected internal edits with observable results, using direct weight changes rather than conventional retraining.

Finding a change that mattered
Astra’s investigation led to a focused change in two of Qwen’s internal layers. The edit touched 131,072 weights, approximately 0.016% of the model, and targeted the behavior associated with its repetitive responses. Edited model documentation
The practical effect is easier to understand than the individual numbers. A model has a limited amount of space to produce its response. When it spends that space repeating itself, it may run out before reaching a usable answer. Reducing that behavior gives it a better chance to complete the work.
This is what makes the experiment compelling: a change to a small part of an existing model made a visible difference to its output. The next step was to measure that difference on questions outside the edit-development process.
What improved in the test
On the original reported MATH-500 evaluation, accuracy rose from 7.9% to 48.1%. The original and edited versions were tested with the same settings, averaging four samples per problem. These evaluation questions were held apart from the questions used while developing the edit. Evaluation protocol and results

Fewer replies exhausted their response budget, and instruction-following results improved too. That broader improvement is useful context: the behavior Astra targeted could interfere with more than math answers. Checkpoint results
The accuracy result and the reduction in unfinished responses complement each other. One measures correct answers; the other helps explain why more answers could reach a conclusion. Both matter when assessing whether an edit makes a model more useful.
This article reports the researchers’ original matched comparison.
Why this is worth watching
The useful possibility is a more direct way to investigate certain model failures. If a problem can be connected to a particular internal behavior, an editing system may be able to propose a focused change and check whether it helps.
That could give model developers another option alongside prompt changes and conventional training. It also changes what we should ask of the evidence. A convincing demonstration needs a traceable edit, a fair comparison and tests beyond the examples used while making the change.
The release includes logs, edit data and reconstruction code, so other researchers can inspect more than the headline result. Released materials
The next question is how reliably this approach transfers to other models and kinds of failure. In a follow-up with a smaller Gemma model that rarely looped, the researchers did not establish a comparable improvement. That points to a useful direction for further testing: identifying which problems respond to targeted edits and which require other approaches. Follow-up experiment
The takeaway
For anyone building with AI, this is a useful reminder to investigate how a model is failing. Wrong reasoning, ignored instructions and unfinished responses may need different fixes, even when they all look like a bad answer to the user.
Astra’s edit is an early example of AI helping with that investigation inside another model. Its value lies in the specific chain the researchers demonstrated: find a recurring failure, make a targeted change, then measure the result on separate tests.
Sometimes, getting more useful work from a model starts with understanding what is getting in its way.
Sources
Sources checked November 9, 2026.
- Rikiya Takehi, Jayden Teoh, Alex Zhang and Omar Khattab, Sparks of Weight-Space Programming, November 2, 2026. Experiment 8 and the Gemma follow-up.
- Edited Qwen3.5-0.8B checkpoint and evaluation documentation. Includes reconstruction details and a separate edited-checkpoint rerun; the article’s before/after comparison uses the original report.
- Experiment logs, edit data and code. Logs and data released under CC BY 4.0; original explanations here are adapted and summarized, not quoted.
- AI research
- AI research
- weight-space programming
- model editing
- Qwen
- evaluation
