Astra can read and write weights to improve Qwen

Re:Astra can read and write weights to improve Qwen by levinb on Monday November 02, 2026 @02:28PM (#50342299)

Just logging in here for the record to state that this property of neural networks is one of the most important aspects of their operation. The convergence of this sort of interoperability, tune-ability, and modularity is probably the most important final frontier in all of ML/AI/software.

Kudos to this fellow for having the temerity, or perhaps even naivete, to discuss it publicly. All my work is private, as I am sure it is inside the big labs.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by orsorna on Monday November 02, 2026 @02:41PM (#50342521)

You acknowledge that you are working on something similar, yet refuse to elaborate and vaguepost...but there is enough information just from your post alone for a dedicated actor to attack you and extract such world-ending information ("world-ending" implied from your ominous reply). Would this not make you as naive as the team that published their findings?

I applaud the authors for sharing their findings and showing real results. Rather than write some bait I would find in an influencer-peddled tweet and allow rampant speculation. It would have been better for you to say nothing.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by levinb on Monday November 02, 2026 @03:00PM (#50342806)

Apologies - you are right. There's some "put up or shut up" to this that's fair play. Also yes, probably naive, or having a less than adaptive response would be true.

I've been tending to my backup plan for a few years, and it's only been in the past year or so that open models were good enough to apply to projects like this, I've been working as hard as I can given my constraints.

This work shows a potential pathway to intepretability, which is actually part of what will give the labs that have it the sort of economy-swallowing capability that for the moment is just IPO hype.

I don't comment here often, but this guy's blog posts are going to go down in Hackernews lore like the original Dropbox posts, and I just want to make sure I'm on the record for this little slice of history.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by stopsayingsorry on Monday November 02, 2026 @03:22PM (#50343144)

>This work shows a potential pathway to intepretability, which is actually part of what will give the labs that have it the sort of economy-swallowing capability

And how would you argument that? From what I see, if anything, it's the opposite.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by igleria on Monday November 02, 2026 @03:19PM (#50343091)

I guess I'll say "I was here too".

When you say interpretability you mean understanding without doubt why an output happened, thus opening the gates for audit-dependant work like accounting?

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by levinb on Monday November 02, 2026 @03:25PM (#50343197)

More like 'models instantly and efficiently adaptable to any use case' and 'what if we could predict all public pricing information accurately, understand why, and know how to act on it'.

I'll leave it at that and get back to work.

[ Parent | on HN ]