If we are purely talking about textbooks, I can see the value in a tool like this... assuming we still have yet to actually solve the problem of AI being able to tell the truth and could just lead to more issues if we can't even read a textbook without it and then learn the wrong thing.

Not to necessarily diss the work that was done on this, but the idea of actually wanting this for reading feels like it is a continuation of the lack of attention span that has seemed to get worse and worse. We already saw this with the oversimplification of television shows and movies. Many of them leaning more towards slapping you in the face with something instead of subtly.

I know way too many people that struggle to sit still for a half hour episode of some show now (like my partner, frustratingly) and have to be doing something else.

If you are struggling with absorbing the information you are reading that is likely a sign you should put down the book and come back to it later, obviously your mind wants to be doing something else. If it is a continued issue than practice reading something that you know you would like. Personally my "in" for my love of reading was reading video game books that expanded the lore and it grew from there, but I was already invested in the story so the book was easier to read.

Using this for a book feels more like a crutch than anything else. That is obviously before you get into whether or not the LLM is actually going to tell you the truth.

There is however one possible use case I could get into, but this is something that could be solved by just finding a video or something online. A refresher when it has been a long time between books coming out in a series.

Thank you very much for your thought-provoking comments.

I actually sympathize with you very much.

As you say, there is a non-zero chance that this app will contribute to a lack of concentration, but I cannot dismiss the possibility that the opposite will happen.

In my case, I have often found myself wanting the crutch of LLM due to lack of prerequisite knowledge when reading technical or philosophical books.

Also, I am an Asian whose English is not that good, and there are times when I have to read a book in its original language because there is no translation in my native language.

This application was created on an experimental basis to remove these panes, and the chat function with LLM is only one function. It should be used at the appropriate time depending on the user's use case.

I don't agree with the OP, AI assisted reading is the future, especially when you're trying to read a tome like War and Peace and don't know all the Napoleonic references or thst the Russian aristocracy spoke French and tried to emulate the French, or why that matters a lot to the plot and your perception of them.

Good job, OP. I wanted to build this myself.

Do you have plans for android and iOS support and syncing across devices?

Some of the books I read are really hard to understand to the point I think the author is deliberately rambling (looking at you Mark Fisher). LLM really help me understand it.

It's interesting that, if this became commonplace, it could be much easier to get value out of poorly written books...

Some people have deep knowledge, but don't have the skills to untangle context and lay out the right learning path for a reader. These people likely bell-curve around certain neurotypes, which perhaps know certain sorts of knowledge more strongly.

Right now, those people shouldn't publish. But if LLMs could augment poorly structured content (not incorrect content, just poorly structured), that perhaps open up more people to share their wisdom.

Anyhow, just thinking out loud here. I'm sure there are some massive downsides that are coming to mind for ppl reading :)

Thanks for your comment. I can see how it could be used successfully for those types of books.

When I was trying to extract as much meaning out of George Eliot's Middlemarch as I could, I would read a chapter, and then upload that chapter's text file (thank you Gutenberg) to NotebookLM. I'd then have it extract unusual vocabulary words, Latin phrases, and cultural/historical references and compare that list to my handwritten notes from my close reading session. It was fun to have a dialog with the LLM about the chapter, and I felt like I got a lot out of it.

At some point I'll work on better integrating Emacs's nov.el EPUB reader with gptel to approximate something like this. Books are text, and I already have the ultimate text processing environment that I've invested quite a lot of time in.

"By conversing with an AI that fully understands the book's content in real time,"

That seems like a maybe a wee bit of an overstatement of possibilities.

You're right to call that out, that's a fair point. "Fully understands" is indeed a bit of an overstatement for the current state of AI.

What I meant from a technical perspective is that the system uses a Retrieval-Augmented Generation (RAG) approach. It has the entire book's content available in a vector database, and when you ask a question, it performs a semantic search to pull the most relevant passages in real-time to use as context for the LLM's answer.

So, from a user's perspective, the experience is designed to feel like you're conversing with an expert who can instantly recall any part of the book. I should have used more precise language. Thanks for keeping me honest!

If this looks hard to install (you need to host a server, supabase, docker, lots of python dependancies) - instead, you could just install this to Edge https://microsoftedge.microsoft.com/addons/detail/epubreader... to use it's built in Copilot sidebar to chat about the book. It would work identical to this project AFAICT, except the back end would be Microsoft.

Thank you for sharing the information/comments. The extensions you have presented are indeed great, but they seem to lack features such as full text search, page count progress tracking, text highlighting, notes, etc. Also, regarding RAG, I find it a bit cumbersome as I have to import the epub every time I open the book. I am not familiar with this tool, so sorry if I am wrong.

Sounds like a cool project. Not sure if it's one that I would personally use, but I think that LLMs can be used wisely.

What I've found interesting when doing similar experiments (feeding things like books to an LLM and asking questions) is that the output is almost always more bland than one would hope for. I suspect this may both be a result of LLMs being biased for the material they've been trained on and a reality I've suspected which is that the majority of books are mostly filler and aren't making points that are particularly profound. Most books, when you distill them down, fundamentally communicate ideas that are rather obvious, but the language around those points makes them sound a lot more profound than they really are. It's a kind of hypnosis, I think. In a sense, LLMs may be able to reveal how bereft a piece of written material is.

I disagree with the OP's statement that traditional e-readers being passive is actually a "problem". It's kind of like saying that cars are a problem because they can't fly. Maybe I'm being pedantic, but being alone with a book and one's own thoughts is hardly a problem; if anything, the problem is fewer and fewer people are comfortable without a constant barrage of thoughts other than their own.

Just seeing the introduction, I can see this tool hardly adds any value.

The introduction video shows how easy it is to import an epub, and then "asks the ebook" to give them the Table of Contents. While the ToC was already available... no real added value compared to RAG

Thank you for your valuable input. As you say, generating a table of contents and summary alone will not be of value. Interacting with the LLM may be helpful when reading documents that are not easily understood, such as difficult technical or academic books.

I saw the ToC request as a demo of the capabilities, not a statement on the full value proposition. There are a LOT of valuable features in here that are not offered in Kindle or other ebook readers.

Haven’t tried the app and not to be disrespectful but I would prefer something like system wide app that can explain the highlighted text anywhere after pressing a shortcut in a tooltip. That way anywhere if you find any word or sentence you want explained you just highlight press shortcut and find out and continue reading, was looking for such app but didn’t find any lightweight single purpose app

Nice! I was also thinking about e-reader with LLM support to discuss topics of the book I'm reading with, explain words or phrases (I'm not a native English reader) and so on. But this seems too troublesome to install and does not have a mobile app - I want to read books on the go, not really in front of my computer. Do you think it's possible to make it phone friendly and easier to install?

Thanks for your comment!

> Do you think it is possible to make it phone friendly and easy to install?

Yes, it is possible. The app supports PWA (Progressive Web Application) and responsive design, so it can be used on mobile by deploying the source code from this Github repository to a cloud environment.

Since this app was originally built exclusively for myself, I have not deployed it to a public cloud for external users to use, but will consider deploying it if users want to.

Another idea is that since this app is OSS, users can deploy it to the cloud themselves.

Can you look into integrating with private book repositories like Calibre? Also, many books on Archive.org are scanned PDFs (usually as images). This would need OCR probably. Would this work with them ? I feel that this would be most useful with old books where the text is not easily searchable, citations are not convenient, or definitions need lookups.

I built https://readboost.io earlier this year. It adds Q&A to quiz yourself to the end of each chapter and lets you download the annotated ePub. Unfortunately, motivation left me after 3 months and it can't handle all books yet. Anyway, it's free to try if anyone is interested.

Is there any mechanism to prevent the AI from answering with spoilers? For example, when I ask about a character I don't want information coming from pages/chapters I still didn't read.

Thank you for the sharp feedback.

Because we've been mainly targeting business and technical books, the spoiler-prevention feature is not yet implemented.

However, to make novels and other narratives comfortable to read in the future, I'll definitely consider adding a feature to limit the AI's knowledge based on your reading progress.

Thanks again for the valuable suggestion!

Claude, is that you?

Since my native language is not English, I use LLM as a translation tool. I am sorry if I have made you feel that the text is inorganic.

Just answer to the best of your ability in English, or if you can't do that then write in your own language and translate that text. The responses currently look like you're asking AI to completely come up with the responses for you rather than including any of your own thoughts.

I guess it’s better for non-fiction books in that case. Similarly I would be upset if the LLM spoiled a fiction book somehow.. like figuring out which characters will die in GoT before reading it.

I also assumed this is for non-fiction books but then I checked the Github page and the first video shows Alice in Wonderland as an example. This is the reason I asked.

Yup, think it's just a poorly chosen example. Although Alice in Wonderland does relate to Mathematics, so maybe it's a better chosen example than we realize!

This is a crucial feature - perhaps implementing a "reading progress tracker" that masks content beyond your current position would make this truly useful for fiction.

wow. I've been entertaining this idea for some time now (Emphasis on "entertaining"). Seeing that already somebody has actually made this makes me very happy.

Will definitely give it a go.

That's fantastic to hear, thank you! It's always validating to know that others have been thinking along the same lines.

I'd love to hear your thoughts once you've had a chance to try it out. All feedback is welcome!

Disclaimer:

I am not fluent in English, so I have included my comments via a translation tool. Therefore, I may offend you with inappropriate language expressions. I apologize in advance.

"Too much thought into whether they could, and not enough thought on whether they should" This is so true. I can't even begin to fathom the implications of this.

A large aspect of the creation of this app was motivated by my curiosity about what the reading experience offered by an e-reader with AI functionality natively integrated into it. Another major reason was that I thought I would have to make it and use it to see if it was really necessary.

Every day I am shocked that books in the public domain on Kindle don't have X-Ray enabled. I am unable to find a copy of War and Peace for instance with X-Ray so I can keep track of all the characters and places. I'm not saying the world isn't going to shit but AI can help fill in feature gaps that the big-box developers have not bothered with.

mega based project, i was thinking about the same. LLMs are very helpful for reading difficult books, or just books requiring previous context. i would add a feature of adding "auto preface" to the book so the reader know what he should know.

Thank you for your empathy. I think it's a great idea to pre-generate concepts and prerequisites that readers might get stuck on.

What does “based” mean to you?

a worthwhile endeavor

Interesting project. I've been thinking about a tool like this; I might be following a multi-volume book series, but it's been years since the last book. When I pick up the latest volume, sometimes there are details that I just can't remember (small details that may turn out important, relationships between minor characters, etc.)

I would just consult a fan wiki, but that doesn't work if the title isn't popular or if the book is too new. This seems like the perfect tool if it can somehow maintain coherency across multiple books.

That said, I do understand (and share) a lot of the frustration and hesitancy that people here have around AI tools; I don't want an app that takes away the act of thinking (like that post recently about teachers using AI to make banal lesson plans, and students in turn using AI to write essays -- what is the point then?). I hope you don't take it too much to heart, and try to showcase use cases where your app can actually provide value.

Another piece of feedback is it would be great if this could be all packaged up into a docker image that would make it easy to deploy on a local machine (or like on a home server/NAS). Right now it seems there are still a lot of manual steps and scaffolding.

Thanks for the feedback!

> That said, I do understand (and share) a lot of the frustration and hesitancy that people here have around AI tools

I share some of the same feelings as well. As for use cases where it can provide value, I think it can be of value if you want to read difficult academic, technical or business books with deep understanding. I think so.

> Right now it seems there are still a lot of manual steps and scaffolding.

I think you are right. I originally planned to use it as a tool for my own exclusive use, so I was able to build an environment with minimal implementation costs, but I didn't expect to get so many comments. I will improve it!

I am glad to hear you say so!

I recently finished a book I was looking forward to but wound up really disliking [0]. Throughout the book I found myself saying "wtf?" and I occasionally would complain to my spouse about it. After I finished reading, I went to Goodreads and enjoyed the schadenfreud of seeing how many other reviewers had the same reaction and reactions as me. I do wonder if a tool like this could help me experience something like this DURING the reading of the book rather than after, but I also worry about it lessening the book reading experience, contributing to attention drain, or lessening the experience of finishing reading a book and talking with others about it.

0 - Brandon Sanderson's Wind and Truth

Thanks for the fantastic feedback! That 'wtf?' moment you described is exactly the kind of problem I was hoping to tackle with BookWith.

You raise a really important point about the risk of lessening the reading experience. That's something I've thought about a lot. My personal experience while using it has been that it can actually deepen immersion, since I'm able to look up a word or phrase instantly without breaking my flow and switching to a browser.

You're absolutely right that this is a new kind of reading experience powered by LLMs, and there are bound to be some downsides. I hope it's an interesting experiment, and I'd be thrilled if you gave it a try.

Thanks again for the valuable perspective!

English is not my first language and I am unfamiliar with it, so I use LLM as a translation tool. I apologize if I have caused any discomfort.

You shouldn’t have to do this but it may be worth adding a note at the end of a comment about this here - accusations of someone being or using LLMs are often thrown out and very rudely (even if correct about the llm use, I don’t think that’s an excuse).

Thanks for building and sharing something.

Thank you for your instruction. I will be careful in the future.

Thank you for sharing this!

I'm disappointed by some of the negative comments. I'm pretty excited about this and plan to try and get this running locally this week. I end discussing a lot of the books I read with ChatGPT, e.g. "hey, this made me think of $idea" or "uh... this is familiar, what am I thinking of?" and to be able to get back a "yeah, check out Ulam's paper on $topic or $book by $author" is really really valuable to me.

I don't read a lot of ePubs (they tend to be mostly PDFs or dead trees) so I might need to adjust a bit, but I'd definitely gonna give something a spin with this.

I am really glad to hear you say that. It's very encouraging. There is still a lot of room for improvement in this application, so please feel free to give us feedback if you have any complaints after actually using it.

Thank you for your comment. As others have pointed out, there is a non-zero chance that it may lead to a decrease in concentration, but the reverse may also be true. I think it would be better to actually try it and see if it fits your skin or not.

I love dystopian novels, so maybe I should give it a go.

I'm constantly finding myself pretty deep into a book and a conversation happens and I have no idea who one of the people are. I'd love a way to just ask my Kindle "who is Uriah Heep?"

> The problem: Traditional e-readers are passive.

Why is that a problem? Your statement is a bit like saying "traditional avocados are too delicious. We at YuckCo are aiming to change that!"

You can't just define something as a problem merely to help you sell a solution.

> When you encounter something unclear, you have to context-switch to search for it.

Literally every eReader I've used has a built in dictionary. I tap the word and it tells me what it means.

How is that context switching but "Hey, Siri, what does the word avocado mean?" isn't?

Why so aggressive? OP created an app that seems very useful for many. You can just ignore it. But you prefer to attack the idea. Why?

Thank you for your consideration of my feelings.

Why are you so interested in defending OP? You could just ignore the commentary, or address the specific issues raised.

Today's phrase that you might want to discuss with an LLM, or a real person:

de gustibus non disputandum

I believe the tone of the comment is the issue, not the substance of the criticism

I think all your points are spot on.

Especially “You can't just define something as a problem merely to help you sell a solution.” is really spot on. It made me pause.

I think it's fair to say that we created this product to test whether LLM can improve the traditional reading experience. And currently, I feel that LLM has somewhat improved the reading experience of technical books.

A dictionary is wildly different from a bank of highlights and notes.

Are you thinking of just books like novels? There’s a lot of reading of technical or scientific or reference material.