Re:Astra can read and write weights to improve Qwen
by qnleigh on Monday November 02, 2026 @06:43PM
(#50345867)
Look at the reasoning the models give before you get too excited here. For the Pong-vs-Pacman example, the model uses observations like small weights for certain arrow keys and large weights where user-controlled objects are. For the language example, it again recognizes some very shallow patterns (Romaji has a limited number of letter groupings) and is taking a 3-option multiple choice test. It's a neat result, but I think the introduction overstates the significance.
[ Parent
| on HN ]
Re:Astra can read and write weights to improve Qwen
by jephs on Monday November 02, 2026 @08:59PM
(#50347029)
Yeah, it definitely looks more magical until you peer behind the curtain, and then it looks obvious. Of course it's all just circuits; of course there are simple patterns to look for in obvious places. But that's with the benefit of cribbing off the thing's work—it's really hellishly clever isn't it, so workmanlike to make such things quotidian.
And of course there's the tendency for LLMs to be completely unable to approach a problem in January, really quite shit in February, rather poor in March, and superhuman in April.