131,072 Weights, and None of Them Were a Math Lesson

A small edit can look like a new skill. Measure the failure you removed before you call the score learning. That is the part worth stealing from a Hacker News thread about models that read and write neural network weights directly. Researchers at MIT CSAIL asked GPT-6 Astra to make Qwen3.5-0.8B better at math by editing weights. No gradients. No... Weiterlesen: 131,072 Weights, and None of Them Were a Math Lesson