No, it describes a linear optimization algorithm from the 01940s editing a Qwen model with billions of parameters.
I think the point being missed is that this same tool that can do the 1940s optimization algorithm can also translate Ancient Greek to English, develop a web app and draw a picture of a pelican riding a bicycle. That’s really crazy.
"In another experiment, they asked Astra to make Qwen3.5-0.8B better at math by editing its weights"
??
I think the point being missed is that this same tool that can do the 1940s optimization algorithm can also translate Ancient Greek to English, develop a web app and draw a picture of a pelican riding a bicycle. That’s really crazy.