Jump to content

BookAngel Idea


Experience

Recommended Posts

So basically, few problems.

Don't want to read the stuff I want to take out, so... an ai or smth would be necessary. Or I guess people that are fine with reading whatever.

And yeah all the problems that vidangel has would become problems but from brothers

Link to comment
Share on other sites

48 minutes ago, Experience said:

So what if

vid angel

but for books?

I don't know if it would even be possible to make cuz all the yucky legal stuff but maybe we could do it?

@Lego Mistborn (I made it. yay)

You're right, there is quite a can of worms there. We'd better get some legal stuff figured out before I get going on making an application.

 

20 minutes ago, Experience said:

So basically, few problems.

Don't want to read the stuff I want to take out, so... an ai or smth would be necessary. Or I guess people that are fine with reading whatever.

And yeah all the problems that vidangel has would become problems but from brothers

Yes, my plan was to utilize an API key to AI (Ideally free, but who knows) to scan and then simply funtional programming to replace the things.

Link to comment
Share on other sites

We need to find all the lawyers of the shard.

I just don't know how to do that. Surely someone does though.

Quote

But i bet some people would do it if they are paid just to edit or take out stuff from an already established book.

I would hesitate to pay someone to do something like this, when I consider(as I expect everyone who is frequenting this thread does) the content to be immoral. I'd much rather use an entity I believe is highly unlikely to have a soul that would be damaged.

P.S. Everyone reading this thread that likes the concept: follow it to get updates if/when I write this program, and drop a like on exp's original post.

Edited by Lego Mistborn
Link to comment
Share on other sites

That is what I'd like to see, but I know that DRM does make it difficult.

I think ebooks would actually be the only format to do this in. Unless you want to build a robot that whites out cuss words and explicit scenes.

If we can verify the legality, we can move forward with design, and after that I can actually get to writing code.

Link to comment
Share on other sites

44 minutes ago, Lego Mistborn said:

We need to find all the lawyers of the shard.

I do debate does that qualify me? :P

I feel like there would be a lot of legal complications for doing anything more than ripping certain pages out of books and lending them to friends.

And with me, I don’t like reading a lot of the stuff but I have enough mental stability that I can get through it without being too affected, especially if I know it’s to get rid of that stuff.

Edited by Edema Ruh
Link to comment
Share on other sites

1 minute ago, Edema Ruh said:

I do debate does that qualify me? :P

I feel like there would be a lot of legal complications for doing anything more than ripping certain pages out of books and lending them to friends.

Perfect. We have ourselves a lawyer :P

Anyone know any authors who we could test this with? Who would be willing to give permission as long as they're payed?

Link to comment
Share on other sites

4 minutes ago, Edema Ruh said:

I mean, the whole of Titus Andronicus…but I think anyone who’s reading Shakespeare is ok with a little violence, and there are so many twists of a lot of his work already.

Okay, but we could use it to figure out the coding and everything. Plus there's always that one person that never wants to read any violence whatsoever so *shrug*

Link to comment
Share on other sites

i do want to say that i kinda think this idea is dumb
like if you can tell the book is getting to a part you think you'd wanna skip
just skip it
skim read until it looks safe

BUT
the idea of making something like this is rather interesting. 

i think you could get a passable program by just looking at word frequency.
like i could totally make this in python in like, an afternoon.

you'd have to already know a little bit about the book, and about the parts you'd want to skip, so you know what words to target.

but then its just a matter of tallying up the number of instances of each word per page (or per paragraph or chapter or anything), and if the frequency of a blacklisted word is too high in a given selection, remove that selection from the text.

also you'd need the entire book in some sort of scannable file format. preferably something simple like a .txt, and that gets questionably legal pretty quickly.

 

Implementing AI is definitely possible and would make something like this far more useful, you could have the AI give a non-descriptive summary of what it's censoring and stuff like that, but that's far out of my wheelhouse. i just know what AI is capable of, no clue how to actually use the APIs or anything. 

the simplest way to implement AI would probably be in tandem with the word frequency model actually. take the clipped section, give it to an AI with a prompt like "summarize this selection of text: [clipped text]. this text is from [book]. Be brief in your summary and remove any explicit material" and take the result and paste it back into the censored book, along with indicators that its not original text. that would actually be really easy to figure out, would just need to figure out how to use gpt plugins n stuff.

Edited by dannnnnnnnnnnnnnnnnnnex
Link to comment
Share on other sites

I would disagree. Sure if an explicit scene is coming you might be able to notice and skip, but how do you know how far to skip? And what if it comes up on you and you didn't notice? Or cuss words that pop up randomly? I think those make this project a valid idea.

Using AI is pretty simple. My plan is to give the AI a text, alongside a prompt like "find all occasions withing this text that are xyz undesirable things" then, with whatever response it returns, remove the offending text.

I should be able to find a way to scan through an EPUB file, as it does contain all the text from the book.

Perhaps a way to do this legally would be to create an ebook reader that works with EPUB and just blurs the location of offensive text. This wouldn't involve actually editing the contents. Lawyer! @Edema Ruh Can you use your debate research skills to find out whether blurring text would be a copyright infringement. We'll want to look at U.S. law, don't worry about the states or other nations' laws yet.

P.S. @dannnnnnnnnnnnnnnnnnnex are you studying CS or do you just a have a working understanding of programming, and what does that knowledge amount to?

Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

Loading...
  • Recently Browsing   0 members

    • No registered users viewing this page.
×
×
  • Create New...