News for hackers. Stuff that matters.
Re:Statement on AI Risk by wongarsu on Tuesday May 30, 2023 @10:06AM (#36125030)
At the extremes you get into the territory of Pascal's Mugging [1]. Which is a delightfully simple example of how our simple methods of stating goals quickly goes wrong

1: https://en.wikipedia.org/wiki/Pascal%27s_mugging

Re:Statement on AI Risk by Jerrrry on Tuesday May 30, 2023 @10:20AM (#36125190)
Is AI Safety a Pascal's Mugging?

[Robert Miles AI Safety]

https://www.youtube.com/watch?v=JRuNA2eK7w0