Qwen 3.8 27B on my laptop can interpret model weights, too

T2Covered by 1 source · first reported by Simon Willison's Weblog at 03 Nov, 16:29 UTC

Yesterday's hot paper was Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights by Rikiya Takehi, Jayden Teoh, Alex Zhang, and Omar Khattab. The paper found that frontier models, in particular GPT-6 Astra, can both interpret and modify the raw weights of a…

ai

Sources

• T2Qwen 3.8 27B on my laptop can interpret model weights, tooSimon Willison's Weblog03 Nov, 16:29