News for hackers. Stuff that matters.

A comment on Astra can read and write weights to improve Qwen. Parent comment

Re:Astra can read and write weights to improve Qwen by taneq on Monday November 02, 2026 @06:16PM (#50345508)
Calling it ‘next-token prediction’ is missing the forest for the trees. The reason prediction gives rise to so many capabilities is that to effectively predict something requires modelling the entities involved and their capabilities. You can’t predict a cat’s next action without knowing how to chase a mouse.
[ Parent | on HN ]
Re:Astra can read and write weights to improve Qwen by monk_grilla on Monday November 02, 2026 @06:34PM (#50345751)
This is a really useful and succinct explanation, I'll be using it, thanks!
[ Parent | on HN ]
Re:Astra can read and write weights to improve Qwen by somberi on Monday November 02, 2026 @08:33PM (#50346850)
taneq - interesting phrasing. Thank you. To extend it to my use case, if you tracked enough Cats moving a certain way, which all resulted in a mouse being caught, then you do not need to know how to catch a mouse yourself. Of all the ways we know a cat can move, these sequences result in a dead mouse, is useful too.
[ Parent | on HN ]