AnalysisAI ModelsNovember 2, 2026

LLMs can natively read and write neural network weights

Read original source →rikiyat.github.io

GPT-6 Astra edited 0.016% of Qwen3.5-0.8B's weights without gradients, lifting MATH-500 from 7.9% to 48.1% and tripling IFEval. It also wrote small game-playing networks from scratch that outplay PPO-trained nets given 100M steps.

How this story unfolded

1 day · 1 report · 5 community posts · 6 of 8 shown

  1. Nov 2
  2. Nov 3

More stories today

Open the live feed