Post
jake
yetanotheruseless.com
did:plc:bjaceaxgoto5p7gor2rcov3g
if you want to understand more about how weird the "using statistics to predict the next word" works out to in practice, you try the mechanistic interpretability work from anthropic:
https://distill.pub/2020/circuits/zoom-in
https://neelnanda.io/mechanistic-interpretability/quickstart
https://transformer-circuits.pub/2021/framework/index.html
2026-09-04T18:42:07.961Z