/explore
|
You are here 
|
www.greaterwrong.com | ||
| | | | |
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... |
|
| | | | | ||
| | | | |
www.alignmentforum.org
Richard Ngo lays out the core argument for why AGI could be an existential threat: we might build AIs that are much smarter than humans, that act aut... |
|
| | | | | ||
| | | | |
blog.evjang.com
The 30th annual Neural Information Processing Systems (NIPS) conference took place in Barcelona in early December. In this post, I share my ... |
|
| | | | | ||
| | | | |
yang-song.net
This blog post focuses on a promising new direction for generative modeling. We can learn score functions (gradients of log probability density functions) on a large number of noise-perturbed data distributions, then generate samples with Langevin-type sampling. The resulting generative models, often called score-based generative models, has several important advantages over existing model families: GAN-level sample quality without adversarial training, flexible model architectures, exact log-likelihood ... |
|
| | | |||
