How has DeepSeek improved the Transformer architecture? (epoch.ai) | HN Screenshots

YHacker Newsscreenshots

Screenshot of epoch.ai: How has DeepSeek improved the Transformer architecture?

First screen, captured 1 year ago.

Looks similar

Screenshot of epoch.ai: Most AI value will come from broad automation, not from R & D

Most AI value will come from broad automation, not from R & D (epoch.ai)

147 points by ydnyshhh 1 year ago | 210 comments

Screenshot of kipp.ly: Transformer Inference Arithmetic (2022)

Transformer Inference Arithmetic (2022)(kipp.ly)

36 points by lawrencechen 3 years ago | 4 comments

Screenshot of manifestai.com: Linear transformers are faster after all

Linear transformers are faster after all (manifestai.com)

94 points by JoelEinbinder 2 years ago | 16 comments

Screenshot of lemire.me: How much do amd64 microarchitecture levels help in Go?

How much do amd64 microarchitecture levels help in Go?(lemire.me)

61 points by zdw 4 months ago | 39 comments

Screenshot of quantamagazine.org: A celebrated cryptography-breaking algorithm just got an upgrade

A celebrated cryptography-breaking algorithm just got an upgrade (quantamagazine.org)

38 points by thunderbong 2 years ago | 2 comments

Screenshot of ethz.ch: ETH Zürich's position on AI in education and ChatGPT

ETH Zürich's position on AI in education and ChatGPT (ethz.ch)

29 points by pandoro 3 years ago | 4 comments