Astra can read and write weights to improve Qwen

Re:Astra can read and write weights to improve Qwen by mlazos on Monday November 02, 2026 @02:21PM (#50342160)

I’m not super impressed by this, LLMs are great at brute forcing and analyzing large amounts of data. It’s literally writing a program except in a programming language we don’t understand.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by lexandstuff on Monday November 02, 2026 @03:19PM (#50343080)

Seems like a pretty big step towards understanding the language no?

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by vessenes on Monday November 02, 2026 @02:47PM (#50342613)

A single forward pass here Bette 10mm+ PPO rounds. You are hard to impress.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by galaxyLogic on Monday November 02, 2026 @02:27PM (#50342285)

So they are reading and analyzing the weights and probabaly run some experiments to see how modifying them will make some answers better. makes sense they can do that.

But how do they know which answers are "better"?

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by bluebands on Monday November 02, 2026 @02:54PM (#50342712)

if they don't loop?

[ Parent | on HN ]