/explore
|
You are here 
|
www.greaterwrong.com | ||
| | | | |
morganredfield.com
|
|
| | | | | One small part of AI safety is being able to make agents that don't play the St. Petersburg coin flipping game (or at least that play it wisely) | |
| | | | |
scottaaronson.blog
|
|
| | | | | Newcomb's Problem, for those of you with social lives, is this. A superintelligent "Predictor" puts two opaque boxes on a table. The first contains either $1,000,000 or nothing, while the second contains $1,000. You have a choice: you can either open the first box or both boxes. Either way, you get to keep whatever you... | |
| | | | |
www.lesswrong.com
|
|
| | | | | The best approach I know for thinking about anthropic problems is Wei Dai's Updateless Decision Theory (UDT). We aren't yet able to solve all problem... | |
| | | | |
www.bretthall.org
|
|
| | | There are two great theories that explain the nature of physical reality. One is quantum theory and the other is general relativity. As science has regained some of its cultural cache over the recent... | ||
