AI 导读
现在很清楚： - 对齐是让 AI 安全的关键 - 对齐无法在少数前沿实验室的闭门造车中解决 所以我们采取两步： - 发起 Open Alignment Initiative，由 @Thom_Wolf @huggingface 领导。 - 申请加入 @DarioAmodei 刚刚承诺的“嵌入式评估者”计划。 让 AI 更透明，从而更安全！
正文
It's now clear that:
- alignment is critical to making AI safe
- alignment won't be solved behind the closed doors of a handful of frontier labs
So we're taking two steps:
- launching the Open Alignment Initiative, led by @Thom_Wolf @huggingface.
- asking to be part of the "embedded evaluators" program that @DarioAmodei just committed to.
Let's make AI safer by making it more transparent!
来源：@ClementDelangue · x.com