Re:Astra can read and write weights to improve Qwen
by tiborsaas on Monday November 02, 2026 @08:02PM
(#50346613)
LLM-s operate in a higher dimensional space and they produces a 1D stream of tokens. We think of the output as all there is to how they work.
It seems like that raw weights are still within the natural language of an LLM and they can easily map weights to a latent space representation, do a transformation and map it back.
I feel that asking about training data is missing the point, they might all be able to do it naturally like I can move in 3D compared to a 2D being living on Flatland.
It seems like that raw weights are still within the natural language of an LLM and they can easily map weights to a latent space representation, do a transformation and map it back.
I feel that asking about training data is missing the point, they might all be able to do it naturally like I can move in 3D compared to a 2D being living on Flatland.