> I really hope to see this improve because the idea is good. The execution is not.

The scraping and storage is simply a search engine. This site would be very valuable if it just presented the information as a search engine - with links to the original documents.

that is a very cool tangential idea imo! thanks, i will consider this.

I see that he's getting downvoted, but there are minor errors indeed. Problem 31 (https://teachyourselfmath.app/problem?id=31) doesn't list the problem inputs, for example.

hey! thanks for pointing this out, checking this.

an update: this is fixed

hey, each problem in itself is intended to be a complete entity. while picking up from the PDF, it is extracting all the text written for that problem. if this is not happening for every problem already, that is something to be fixed I believe. i would rather spend my time in making this better instead of curating every problem manually. i could also spend time in picking up better sources that have more complete problems in general.

thank you for your feedback!

A thought. If you're set on automation it could be that you could try automating the opposite of this approach as well. Detecting incomplete problem definitions when they happen.

In either case, you're welcome. I don't mean to be rude :) As I said I think it's a good idea. I just know that poor execution on this will limit the potential a lot.

yep - a cleanup job running at a set frequency seems like a good idea! and no worries, i am taking all the feedback positively. thank you for taking the time to share your thoughts!

Because that's arguably the next step. Why doesn't he solve them while he's at it? Efficiency is lost here!

What's wrong with this problem?

The problem seems to have been fixed? Another poster under my top level comment posted a similar one that is missing crucial information.

Makes sense, I was confused.

I don't see what's upsetting about the problem you linked. If you don't know what a "greatest common divisor" means, why not search it or put it into GPT? That's the simplest statement of the problem.

He fixed it, which is good.