/explore
|
You are here 
|
joecarlsmith.com | ||
| | | | |
www.alignmentforum.org
I've written a draft report evaluating a version of the overall case for existential risk from misaligned AI, and taking an initial stab at quantifyi... |
|
| | | | | ||
| | | | |
reflectivealtruism.com
I take a second look at the Carlsmith report on risks from power-seeking artificial intelligence, focusing on Carlsmith's argument for instrumental convergence. |
|
| | | | | ||
| | | | |
www.cold-takes.com
Today's AI development methods risk training AIs to be deceptive, manipulative and ambitious. This might not be easy to fix as it comes up. |
|
| | | | | ||
| | | | |
www.seangoedecke.com
|
|
| | | |||
