注册并分享邀请链接,可获得视频播放与邀请奖励。

Anthropic
@AnthropicAI
We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on
加入 January 2021
2 正在关注    2M 粉丝
Using MSM, we can also empirically study which model specs or constitutions yield the best generalization from alignment training. Specifying rules works to some extent, but explaining the values underlying those rules (or adding more detailed subrules) is even better.
显示更多
0
16
150
7
转发到社区