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. crop_r+Zm
[view]
[source]
2023-07-05 18:24:09
>>User23+Sj
You can if you are the one controlling their resource allocation and surrounding environment. Similar to how kings kept smartest people in their Kingdom in line.
◧◩◪
3. tester+mr
[view]
[source]
2023-07-05 18:39:42
>>crop_r+Zm
Only works for so long. A smart enough serf could easily find a way to socially engineer and slaughter the king.
[go to top]