- cross-posted to:
- fediverse@lemmy.ml
- cross-posted to:
- fediverse@lemmy.ml
You must log in or register to comment.
Anyone know:
How to rip a wiki from something like fandom and save it in a format that could be uploaded to this and
If that’s legal in the first place?
It’s legal if credit is given and it’s shared under CC-BY-SA.
https://www.fandom.com/licensing
Except where otherwise permitted, the text on Fandom communities (known as “wikis”) is licensed under the Creative Commons Attribution-Share Alike License 3.0 (Unported) (CC BY-SA).
you might find some inspiration from https://breezewiki.com/ - either its codebase directly or using it as an intermediary while scraping
- Paste each article’s raw source to ChatGPT, ask it to do it for you. If there are too many, you can automate it through the API for a negligible cost.
- Is it not.
Maybe also wget the website.
I’d be careful with using “ai.” Sometimes ChatGPT makes up answers even when you provide it with the data. -source it lies to me all the time
Converting from one format to another, it can do like gangbusters. I wouldn’t trust it to summarize stuff from its training data, it can do a little bit better with summarizing stuff you give it, but just mechanically finding the text and putting it verbatim into a different markup it’s pretty capable with.
Even reformatting has caused me issues. My best example is I gave it 100 citations in a non standardized format and asked for MLA. It returned 100 in MLA but randomly 10 of the books were made up. It decided to delete ten I sent at random and make them up instead of just giving me what I sent
Oh… yeah, you might have a point. Beyond a certain size of repeated things, it sometimes goes haywire, I’ve seen that.
I didn’t consider length! That’s a good point too
Another goofy example is I asked it a python question using a specific package import . I sent a big chunk of code. It answered using a package I wasn’t even importing breaking everything. It could never figure it out either lol
Yeah, that kind of thing requires reasoning, and it goes awry almost immediately. It’s still pretty useful for generating snippets of boilerplate or finding stuff in big chunks of code, but I more or less gave up on having it actually create anything nontrivial in code.
This is a cute idea but I’ve generally been satisfied with the idea of using Gitit. That’s a wiki backed by a git repo, so you can use normal git commands to propagate updates between servers. https://github.com/jgm/gitit or “apt install gitit”.
