/explore
|
You are here 
|
www.lesswrong.com | ||
| | | | |
distill.pub
|
|
| | | | | If we want to train AI to do what humans want, we need to study humans. | |
| | | | |
www.greaterwrong.com
|
|
| | | | | This is a new introduction to AI as an extinction threat, previously posted to the MIRI website in February alongside a summary. It was written independently of Eliezer and Nate's forthcoming book, If Anyone Builds It, Everyone Dies, and isn't a sneak peak of the book. Since the book is long and costs money, we expect this to be a valuable resource in its own right even after the book comes out next month.[1] The stated goal of the world's leading AI companies is to build AI that is general enough to do anything a human can do, from solving hard problems in theoretical physics to deftly navigating social environments. Recent machine learning progress seems to have brought this goal within reach. At this point, we would be uncomfortable ruling out the possibi... | |
| | | | |
multiverseaccordingtoben.blogspot.com
|
|
| | | | | I recently wrote a blog post about my own AI project , but it attracted a bunch of adversarial comments from folks influenced by the Singula... | |
| | | | |
opentheory.net
|
|
| | | [AI summary] The text presents a critique of the Foundational Research Institute's (FRI) approach to defining and addressing suffering and s-risks, with a focus on the philosophical and metaphysical challenges of functionalism. The author, Mike Johnson, argues that FRI's reliance on functionalism leads to intractable problems, such as the inability to provide a clear, disagreement-mediating definition of suffering. He outlines several objections to FRI's position, including the ineffability of suffering, intuition duels, convergence requirements, and the mapping of consciousness to physical systems. Johnson suggests that FRI should consider alternative frameworks, such as computational hierarchies, to address these issues. The text also references various so... | ||
