News for hackers. Stuff that matters.
Re:Qwen3.8 is launching and going open-weight soon by worldsavior on Sunday July 19, 2026 @05:55AM (#48966526)
That's a 2.4T model, how would they reduce this to 35B and still give some accuracy? That's a completely different arch.
Re:Qwen3.8 is launching and going open-weight soon by cyanydeez on Sunday July 19, 2026 @07:24AM (#48967064)
there's been a lot of research about reducing models by taking out layers; there's also using it to train smaller models by optimizing parameters.

I dont see most model building as anything more than a pig at a slop troth, despite the level of sophistication; they're still rarely pruning the input beyond random sampling.