News for hackers. Stuff that matters.
Re:Astra can read and write weights to improve Qwen by hashmap on Monday November 02, 2026 @11:57PM (#50348259)
What I have been reading makes me want to both agree and disagree with your take here. I think the fact that some of these things are not only established but are much simpler than one would think at first glance yields the much cooler realization that you can not only do a lot more than abliteration, but that humans can do it by hand if the thing is made legible.

From my experience with models when it comes to discernment about particular things, the models, even the best ones, still are not very good. The thing that we are most missing I think is acceleration in creating editing tools for humans that make the otherwise inscrutable both visually legible and interactive.

Re:Astra can read and write weights to improve Qwen by junofan on Tuesday November 03, 2026 @01:18AM (#50348696)
At least the Qwen3.5-0.8B loop bug isn’t that special (or rather not something worth extrapolating). I literally had this issue last week and told Astra to just go fix it.
Re:Astra can read and write weights to improve Qwen by versteegen on Tuesday November 03, 2026 @06:01AM (#50350439)
...and did it? What did it do?