https://www.alignmentforum.org/posts/HBxe6wdjxK239zajf/what-failure-looks-like
There are many benefits and many risks from AI/Machine Learning. Some of them are more plausible than others. Some are easier to understand than others. The “AI Alignment Probe
Among the plausible, serious problems that The Alignment Problem. Paul Christiano’s article has a very strong and clear explanation of part of this problem.
The stereotyped image of AI catastrophe is a powerful, malicious AI system that takes its creators by surprise and quickly achieves a decisive advantage over the rest of humanity. …
