Enigma: GPT-2 trained on 10K Nature Papers: Can you spot the difference?

Re:Enigma: GPT-2 trained on 10K Nature Papers: Can you spot ... by drusepth on Thursday May 13, 2021 @07:02PM (#27148576)

I use GPT-2/3 in creative writing to generate rough text that I then go back and edit/improve because it gives a good starting point (and often has a lot of high-quality factors).

I don't know if this translates to technical writing, but it's possible someone might complete a prompt on some specific topic(s) and then use that as a point to start from, especially if they're knowledgeable enough on the topic to correct the output. It's nice to be able to skip a lot of boilerplate words (how many words in this comment are actually the meat of this idea, and how many words are just there to tie all those morsels together?)

[ Parent | on HN ]

Re:Enigma: GPT-2 trained on 10K Nature Papers: Can you spot ... by bulldog13 on Friday May 14, 2021 @08:13AM (#27153368)

What platform do you use ? Is it all run from home ?

[ Parent | on HN ]

Re:Enigma: GPT-2 trained on 10K Nature Papers: Can you spot ... by drusepth on Tuesday May 18, 2021 @03:33PM (#27199869)

I built my own editor on top of the API, which I ran at home, yeah. You can see the code and/or run it yourself at https://github.com/indentlabs/gpt-3-writer, but it's very rough and not really ready for public use. Just make sure your OpenAI secret key is set in ENV['OPENAI_SK'] and you should be able to run it yourself.

I also built a more polished version to add to the Notebook.ai document editor (so writers can get some continuation prompts whenever they get a bit of writer's block), but the pricing made it unfeasible to actually release. Notebook.ai is also open source though, and you can see the GPT-3 functionality in the unmerged PR here: https://github.com/indentlabs/notebook/pull/739

[ Parent | on HN ]