|
You are here |
blog.ncase.me | ||
| | | | |
www.lesswrong.com
|
|
| | | | | (Independent) alignment researchers need to be exceptionally good at philosophy of science In order to be effective, independent AI alignment/safety/... | |
| | | | |
www.lesswrong.com
|
|
| | | | | AI used to be a science. In the old days (back when AI didn't work very well), people were attempting to develop a working theory of cognition. ... | |
| | | | |
www.lesswrong.com
|
|
| | | | | Part of the sequence:The Science of Winning at Life ... | |
| | | | |
www.alignmentforum.org
|
|
| | | This is the fourth post in a sequence of posts that describe our models for Pragmatic AI Safety. ... | ||