News for hackers. Stuff that matters.

A comment on Astra can read and write weights to improve Qwen.

Re:Astra can read and write weights to improve Qwen by neom on Monday November 02, 2026 @08:27PM (#50346802)
Someone familiar with this stuff able to enlighten me how this technique differs from this 2024 research? Refusal in Language Models Is Mediated by a Single Direction: https://arxiv.org/html/2406.11717v3
[ Parent | on HN ]

There are no comments on this comment yet.