Jan Leike 谈 Opus 4.5 对齐做法
Some people have been asking what we did to make Opus 4.5 more aligned.
AI 导读
有人问我们对 Opus 4.5 做了哪些对齐工作。 我们计划写很多细节，但最重要的是，对齐研究员深度参与后训练，并有很大的改动空间。
查看原帖From everything we know so far, Opus 4.5 seems to be the best-aligned model out there in a bunch of ways. I follow the training process closely as part of my work on alignment evaluations. Here's my guess about the two things that are most responsible for making 4.5 special. 🧵
正文
当前显示原文，中文全文译文尚未就绪。
Some people have been asking what we did to make Opus 4.5 more aligned.
There are lots of details we're planning to write up, but most important is that alignment researchers are pretty deeply involved in post-training and get a lot of leeway to make changes.