Astra can read and write weights to improve Qwen

Re:Astra can read and write weights to improve Qwen by jonplackett on Monday November 02, 2026 @03:08PM (#50342936)

Is there any chance they’ve just seen these weights before and are recognising them?

If not this is mind blowing.

However it would be interesting to k ow if it can understand its own weights, not just weights much simpler than itself.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by xpct on Monday November 02, 2026 @04:11PM (#50343824)

By no means I'm saying this isn't impressive, but I think this is another case of LLMs being good at translating semantic meaning between different representations.

Obvious ones are spoken languages and code, but they can also natively interpret some simpler ciphers, hashes or simpler encodings, partly (I think) because it was in their training data.

As others have postulated, if they've been ingesting raw weights, naturally they learn how to translate semantic meaning to matrices.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by jonplackett on Tuesday November 03, 2026 @04:43AM (#50349940)

Do you think that means they’d be able to understand and improve their own weights? Or only less complex ones than themself

[ Parent | on HN ]