zlacker

[return to "Introducing Superalignment"]
◧
1. User23+Sj[view] [source] 2023-07-05 18:13:07
>>tim_sw+(OP)
> How do we ensure AI systems much smarter than humans follow human intent?

You can't, by definition.

◧◩
2. cubefo+Te1[view] [source] 2023-07-05 22:34:12
>>User23+Sj
You can, at least in principle, shape their terminal values. Their goal should be to help us, to protect us, to let us flourish.
[go to top]