'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 ...
GitHub

Logs: LLMs can understand and write neural network weights

Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights' - RikiyaT/lm_understand-logs ...
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 route in advanced artificial intelligence and neural network engineering.
GitHub

DEB ML Init

To obtain a DEB model, the calibration problem must be solved: find the parameters that minimize the deviation between observed data and model predictions. While DEB model calibration is largely ...

Ben Affleck Explains How He Writes Code and Gets VIP Access to Top AI Labs

Ben Affleck writes Python, understands convolutional neural networks, and used his celebrity status to get private looks at ...
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.
xenospectrum

MIT Shows an LLM Can Read and Edit Another Neural Network's Weights Directly

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 ...
India Today on MSN

Can AI fix another AI's brain? MIT researchers use GPT-6 Astra to boost Qwen's maths skills

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.
lapaasvoice.com

MIT Uses GPT-6 Astra to Boost Alibaba’s Qwen Math Performance by Editing Just 0.016% of Its Weights

Researchers at the Massachusetts Institute of Technology (MIT) have used OpenAI’s GPT-6 Astra to improve the mathematical performance of Alibaba’s Qwen3.5-0.8B AI model by directly modifying… ...
BIOENGINEER

Graph neural network model learns design element links for sharper style transfer

A new study proposes a graph neural network tuned by a modified zebra optimization algorithm that models relationships among ...
ShiftDelete.Net

GPT-6 Astra Edits Qwen Weights Directly, Lifting Math Scores 6x

MIT researchers say GPT-6 Astra edited 0.016% of Qwen3.5-0.8B weights without training, fixing reasoning loops and lifting MATH-500 from 7.9% to 48.1%.
BIOENGINEER

Neural Network Learns to Predict Carreau Nanofluid Flow in Seconds

A Bayesian-regularized neural network trained on numerical solutions predicts velocity, temperature, concentration and ...