an AI just did brain surgery on another AI lolmit researchers gave gpt-6 astra the raw weights of a tiny qwen model and said: make it better at math. no training allowed.it found what made the model loop forever and edited 131,072 weights. that's 0.016% of the model.math-500 went from 7.9% to 48.1%.the catch: same trick did nothing on a model that didn't loop. it removed a blocker, it didn't add a skill.https://rikiyat.github.io/blog/weight-space-programming/#AI #LLM #MachineLearning
an AI just did brain surgery on another AI lolmit researchers gave gpt-6 astra the raw weights of a tiny qwen model and ...
