Uploaded November 2026 | Updated November 2026, 1 day ago
Researchers at MIT have found that frontier LLMs are surprisingly good at natively reading and writing neural network weights. Just by looking at the raw weights, GPT-6 Astra can tell what a network was trained to do, and even write, from scratch, small game-playing networks that outplay networks trained for 100 million steps.
---
Link to blog post: rikiyat.github.io/blog/weight-space-programming
X: twitter.com/garyexplains
GitHub: github.com/garyexplains
#garyexplains
Researchers at MIT have found that frontier LLMs are surprisingly good at natively reading and writing neural network weights. Just by looking at the raw weights, GPT-6 Astra can tell what a network was trained to do, and even write, from scratch, small game-playing networks that outplay networks trained for 100 million steps.
---
Link to blog post: rikiyat.github.io/blog/weight-space-programming
X: twitter.com/garyexplains
GitHub: github.com/garyexplains
#garyexplains










