Re:Astra can read and write weights to improve Qwen
by bicepjai on Monday November 02, 2026 @07:36PM
(#50346388)
Recently Steven Strogatz said in a podcast,
>> “If you ask it, how did you solve the Navier-Stokes Millennium problem? It gives a crappy explanation.
It can't explain itself very well. Maybe it will get better at explaining itself. Even if it does, I think it will become so advanced so soon, that even the best, most patient pedagogical teacher will not be able to explain itself to us because it'd be like me teaching calculus to my dog.
My dog can't understand it. I'm too advanced for it. And I think we are going to be in the relation to AI that my dog is to me soon.”
Now I am sure we are definitely in a better place in interpretability research than a year ago. But this finding that the llm knows what weights to adjust so it gets predictable behavior of another llm takes interpretability to another level; makes me think we are “Strogatz-dogs” now
>> “If you ask it, how did you solve the Navier-Stokes Millennium problem? It gives a crappy explanation. It can't explain itself very well. Maybe it will get better at explaining itself. Even if it does, I think it will become so advanced so soon, that even the best, most patient pedagogical teacher will not be able to explain itself to us because it'd be like me teaching calculus to my dog. My dog can't understand it. I'm too advanced for it. And I think we are going to be in the relation to AI that my dog is to me soon.”
Now I am sure we are definitely in a better place in interpretability research than a year ago. But this finding that the llm knows what weights to adjust so it gets predictable behavior of another llm takes interpretability to another level; makes me think we are “Strogatz-dogs” now
From The Daily: When A.I. Comes for Your Purpose in Life, Oct 13, 2026 https://podcasts.apple.com/us/podcast/the-daily/id1200361736...