Live data from Hacker News

Reading problems aren't a willpower issue – your brain got rewired

news.ycombinator.com

11–15 of 15 posts

Re: Reading problems aren't a willpower issue – your brain got rewired

#11
post #5

> your brain got rewired Rewire it back! You're acting like this is basically a one-way door when it's not. Just read a book without picking up your phone for 30 minutes a day. It's not that complicated. > Smart people, curious people, people who wanted to read. If they wanted to read they'd be doing it.

I mean yes. It can be rewired back. But I think twitter (specifically for me) is required for my industry. I try to limit it to 30 min a day, but still I cannot cut it completely. There are concentration exercises that can be done, but they are demanding...

> There are concentration exercises that can be done, but they are demanding...

Well you get to decide what you dislike more, having a terrible attention span or doing demanding concentration exercises.

Re: Reading problems aren't a willpower issue – your brain got rewired

#14
post #7
post #3

You started this post as a story, but buried the lede in that you're advertising your service - you should be upfront about this. And it's funny that you said that you're "building one ... for myself", while asking $30/month for the cheapest plan. For that kind of money, I would expect it to include a book subscription - as a reference, Kindle Unlimited is $12/month. As for the implementation - how can you ensure tha…

To guarantee that it does not illuminate and stays on track, I pass the relevant chapters in the context window, I pass the topics to cover, the ones already covered and the latest messages exchanged. So highly relevant content as input and a refined prompt do the trick.

But context is only additive. You can give it the book content, but I don't think there's anything you can do to prevent it from bringing in unrelated info, unless you have a separate non-AI layer (e.g. connected to the RAG) that gives the user the particular snippets from the book, but even then you can't control what the AI bring to its interpretation of these snippets.

One thing that I think could be nice is if you could have it always keep the book in view, and just scroll to the appropriate place it is referring to, and then somehow highlight the specific snippet it is currently referring to, so that I could visually verify that it's giving me "grounded" information. Does your system do something like that?

Re: Reading problems aren't a willpower issue – your brain got rewired

#15
post #7

Earlier quoted context omitted.

To guarantee that it does not illuminate and stays on track, I pass the relevant chapters in the context window, I pass the topics to cover, the ones already covered and the latest messages exchanged. So highly relevant content as input and a refined prompt do the trick.

But context is only additive. You can give it the book content, but I don't think there's anything you can do to prevent it from bringing in unrelated info, unless you have a separate non-AI layer (e.g. connected to the RAG) that gives the user the particular snippets from the book, but even then you can't control what the AI bring to its interpretation of these snippets. One thing that I think could be nice is if yo…

It currently does not do that. It's a different way to "experience" a book. There's an argument where, like you proposed, book and tutor are on at the same time. I will keep it in mind
Post reply on HN