MrUssek | Dark Hacker News

1.	China has trained a 10 trillion parameter language model(twitter.com) 4 points by MrUssek 4 years ago \| 0 comments
2.	What is your backup if the tech industry crashes? 4 points by MrUssek 4 years ago \| 10 comments
3.	4 years ago \| discuss
4.	The Future of Deep Learning Is Photonic(spectrum.ieee.org) 1 points by MrUssek 4 years ago \| 0 comments
5.	Separating MNIST digits using Optimal Transport(mrussek.com) 1 points by MrUssek 4 years ago \| 0 comments
6.	Enigma: GPT-2 trained on 10K Nature Papers: Can you spot the difference?(stefanzukin.com) 183 points by MrUssek 5 years ago \| 105 comments
7.	GShard: Scaling giant models with conditional computation and automatic sharding(arxiv.org) 112 points by MrUssek 5 years ago \| 35 comments