Tech Times on MSN

Tsinghua study: AI coding agents cut costs 26% by rewriting their own scaffolding

Tsinghua's HarnessPro cuts AI coding agent costs 26% while boosting accuracy without model retraining. Factory Droid 1.0 ...

'Like gene editing for neural networks': MIT researchers used GPT-6 Astra to edit Qwen's open weights directly, boosting math performance

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 ...

Just Splitting Mahjong Tiles Leads to a Massive Flowchart—The Invention of Recursive Functions

When studying programming, you notice something strange.Processes that are extremely complex for humans to think through can sometimes be written surprisingly concisely using functions.A prime example ...
eu.36kr

MIT allowed GPT-6 Astra to directly modify Qwen's weights, and its math scores have soared.

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

F1 Race Pace Forecasting

The frozen RF/B1 comparison uses saved predictions; analysis never refits or predicts again. Every group table includes lap/race counts, equal-race mean MAE, pooled lap MAE, gains and race wins/losses ...
news.lavx.hu

LLMs read and edit neural weights without gradients

Astra identifies game policies from raw weight matrices and fixes reasoning loops in Qwen3.5-0.8B by editing 0.016% of parameters, lifting MATH-500 scores from 7.9% to 48.1% without training loops.