Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights' - ...
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 ...
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 ...
Unlock the transformative power of self-programming with our comprehensive guide on "I 'Program' Myself" — a strategic, ...
I have decided to make November 2026 a month for studying AI in earnest. Although I have been using generative AI, including ...
A Day of Reverse Engineering and AI AgentsRead today's top 10 in one goToday's lineup features a mix of reverse engineering, ...
The MIT CSAIL team has proposed a "weight-space programming" method that enables GPT-6 Astra to directly read and modify ...
You're currently following this author! Click to unsubscribe from email alerts. Ben Affleck is once again surprising people with his AI chops. The movie star conveyed an impressive understanding of ...
Ben Affleck writes Python, understands convolutional neural networks, and used his celebrity status to get private looks at ...
A PyTorch implementation of Binarized Neural Networks (BNNs) with Shift-based Batch Normalization and AdaMax optimizer. - Wzx0110/PyTorch-BNN-Reimplementation ...
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.
Simon Willison ran the 17-gigabyte open-weight model locally and fed it floating-point arrays from four reinforcement-learning policies. Without calculators or code execution, Qwen identified Breakout ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results