Instead of writing code, try giving the blueprint to AIRecently, I have been creating various programs using generative AI ...
On November 2, 2026, four researchers including Rikiya Takehi from MIT CSAIL (Computer Science and Artificial Intelligence ...
The MIT CSAIL team has proposed a "weight-space programming" method that enables GPT-6 Astra to directly read and modify ...
Jeff Dean left Google after 27 years to found Discovery Loop, a startup automating research loops to run thousands of ...
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 ...
MIT CSAIL finds GPT-6 Astra can read and write neural weights directly, fixing Qwen3.5-0.8B math from 7.9% to 48.1% with a 0.016% edit and no gradients.
Weight-space programming explores how an agent can inspect, construct, or modify neural network parameters to implement a specified behavior. This collection connects direct LLM-driven experiments to ...
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 ...
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.
GPT-6 AstraがLLMの重みを直接書き換えて数学の正答率を約6倍にしたらしい。しかも変更したのは全体のわずか0.016%で、勾配降下も追加学習もしていないという... これ、AIが別のAIの内部構造を理解し始めてるってことなのか……? 詳しく見てみると、対象はQwen3.5-0.8Bで、MATH-500の正答率が7.9%から48.1%、GSM8Kも13.8%から67.1%に改善している。
MIT has unveiled an innovative, groundbreaking paradigm dubbed "Weight Space Programming", representing a transformative new ...
At TechSparks 2026, Intuit’s Principal AI Scientist explained why reliable tools, high-quality data, and consent matter more ...