5 Matching Annotations
- Feb 2024
-
arxiv.org arxiv.org
-
T. Herlau, "Moral Reinforcement Learning Using Actual Causation," 2022 2nd International Conference on Computer, Control and Robotics (ICCCR), Shanghai, China, 2022, pp. 179-185, doi: 10.1109/ICCCR54399.2022.9790262. keywords: {Digital control;Ethics;Costs;Philosophical considerations;Toy manufacturing industry;Reinforcement learning;Forestry;Causality;Reinforcement learning;Actual Causation;Ethical reinforcement learning}
-
-
pdf.sciencedirectassets.com pdf.sciencedirectassets.com
-
Can model-free reinforcement learning explain deontological moraljudgments?Alisabeth AyarsUniversity of Arizona, Dept. of Psychology, Tucson, AZ, USA
-
- Jul 2023
-
-
That's the way computers are learning today. 00:02:35 We basically write algorithms that allow computers to understand those patterns… And then we get them to try and try and try. And through pattern recognition, through billions of observations, they learn. They're learning by observing. And what are they observing? They're observing a world that's full of greed, disregard for other species, violence, ego, 00:03:05 showing off The only way to be not only intelligent but also to have the right value set is that we start to portray that right value set today. THE PROBLEM IS UNHAPPINESS
- Machine learning
- will learn all our bad habits
- and become supercharged, amplified versions of them
- The antidote to apocalyptic machine learning
- is human happiness and wisdom
- Machine learning
-
-
docdrop.org docdrop.org
-
even though the existential threats are possible you're concerned with what humans teach I'm concerned 00:07:43 with humans with AI
- It is the immoral human being that is the real problem
- they will teach AI to be immoral and with its power, can end up destroying humanity
-
a nefarious controller of AI presumably could teach it to be immoral
- bad actor will teach AI to be immoral
- this also creates an arms race as "good" actors are forced to develop AI to counter the AI of bad actors
-