Early Access Video: AI That Doesn't Try Too Hard - Maximizers and Satisficers (Patreon)
Published:
2019-08-21 14:49:46
Imported:
2023-12
Content
Powerful AI systems can be dangerous in part because they pursue their goals as strongly as they can. Perhaps it would be safer to have systems that don't aim for perfection, and stop at 'good enough'. How could we build something like that?
https://www.youtube.com/watch?v=Ao4jwLwT36M
[I keep doing these videos with animation, and it always takes forever...]