News for hackers. Stuff that matters.
Re:AI training method exceeds GPT-3 performance with fewer p... by m3at on Wednesday October 07, 2020 @12:51AM (#24705418)
If you want to read the source, I recommend skipping to their follow-up paper (same authors): https://arxiv.org/abs/2009.07118

Edit: tangentially related but for those who like to have a glance from their phone, arxiv-vanity is great instead of squinting at a pdf: https://www.arxiv-vanity.com/papers/2009.07118/

Re:AI training method exceeds GPT-3 performance with fewer p... by throwawayiionqz on Wednesday October 07, 2020 @10:44AM (#24708779)
What is wrong with opening the PDF on a phone?

Arxiv vanity has issues. Figure 2 in the paper you listed doesn't display correctly. I am not sure the author would agree or be happy that arxiv vanity reproduces their work into a webpage with sub-par rendering.

Re:AI training method exceeds GPT-3 performance with fewer p... by Jugurtha on Wednesday October 07, 2020 @07:25AM (#24707147)
Nice. We're building a machine learning platform[0] where you can schedule a training notebook job, watch it on your phone. Examples[1][2]. Docs[3]

- [0]: https://iko.ai

- [1]: https://twitter.com/jugurthahadjar/status/130762501783286989...

- [2]: https://twitter.com/jugurthahadjar/status/131380072874244915...

- [3]: https://iko.ai/docs/notebook/#long-running-notebooks

Re:AI training method exceeds GPT-3 performance with fewer p... by Jugurtha on Wednesday October 07, 2020 @10:31AM (#24708621)
Just to clarify. This is about the fact it's cool to be able to read/consult what usually is better suited for a larger monitor, such as content from arxiv, or ML workloads. The links I shared are relevant because of that.