註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Morgan
@morganlinton
cofounder @boldmetrics / studying how llms think @vulcanbench / early @sonos views are my own
加入 January 2009
1.2K 正在關注    47.9K 粉絲
Not sure ppl realize what a big deal this is.
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog:
顯示更多