/explore
|
You are here 
|
www.greaterwrong.com | ||
| | | | |
www.lesswrong.com
|
|
| | | | | Machine learning has been outpacing safety. Ten years ago, AlexNet pushed the boundaries of machine learning, and it was trained using only two GPUs.... | |
| | | | |
www.alignmentforum.org
|
|
| | | | | AI researchers warn that advanced machine learning systems may develop their own internal goals that don't match what we intended. This "mesa-optimiz... | |
| | | | |
vkrakovna.wordpress.com
|
|
| | | | | (This post is based on an overview talk I gave at UCL EA and Oxford AI society (recording here). Cross-posted to the Alignment Forum. Thanks to Janos Kramar for detailed feedback on this post and to Rohin Shah for feedback on the talk.) This is my high-level view of the AI alignment research landscape and... | |
| | | | |
rsbakker.wordpress.com
|
|
| | | "Studying history aims to loosen the grip of the past," Yuval Noah Harari writes. "It enables us to turn our heads this way and that, and to begin to notice possibilities that our ancestors could not imagine, or didn't want us to imagine" (59). Thus does the bestselling author of Sapiens: A Brief History of... | ||
