Astra can read and write weights to improve Qwen

Re:Astra can read and write weights to improve Qwen by stingraycharles on Monday November 02, 2026 @06:16PM (#50345509)

Don’t forget that weights of models and their behavior may, perhaps unintentionally, be in their training set.

Or at least those of some models, and I wouldn’t be surprised that an LLM model is able to understand correlations between weights and behavior better than humans could ever do.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by hackernud3s on Monday November 02, 2026 @07:11PM (#50346182)

So their weights are in their weights? Doesn't that double their weights?

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by stingraycharles on Monday November 02, 2026 @10:06PM (#50347514)

Not in that way, more that they can predict what good or bad relations between weights would look like.

[ Parent | on HN ]