zlacker

[return to "Introducing Superalignment"]
1. voldac+sb1[view] [source] 2023-07-05 22:15:29
>>tim_sw+(OP)
>How do we ensure AI systems much smarter than humans follow human intent?

What is human intent? My intents may be very different from most humans. It seems like ClosedAI wants their system to follow the desires of some people and not others, but without describing which ones or why.

◧◩
2. aidenn+mx1[view] [source] 2023-07-06 00:32:36
>>voldac+sb1
Sure, there are some humans who want to destroy all of humanity, but that seems to be twisting the obvious meaning of "human intent" in this context.

They have been very clear on "why." The goal is to prevent enslavement and/or extinction of the human race by a super-intelligent AI.

[go to top]