/explore
|
You are here 
|
www.alignmentforum.org | ||
| | | | |
www.lesswrong.com
|
|
| | | | | Our alignment research aims to make artificial general intelligence (AGI) aligned with human values and follow human intent. We take an iterative, em... | |
| | | | |
joecarlsmith.com
|
|
| | | | | A high-level picture of how we might get from here to safe superintelligence. | |
| | | | |
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) | |
| | | | |
xorshammer.com
|
|
| | | Let $latex \mathrm{PA}$ be Peano Arithmetic. Gödel's Second Incompleteness Theorem says that no consistent theory $latex T$ extending $latex \mathrm{PA}$ can prove its own consistency. (I'll write $latex \mathrm{Con}(T)$ for the statement asserting $latex T$'s consistency; more on this later.) In particular, $latex \mathrm{PA} + \mathrm{Con}(\mathrm{PA})$ is stronger than $latex \mathrm{PA}$. But certainly, given that... | ||
