Probably a great project, but I couldn't use it as it shows me all book titles in German. Obviously it is based on my IP address. But I'm not a German speaker, so I'd like to control this behavior.
Unfortunately, it seems that some modern websites, including Google, tend to prioritize IP address over user preferences when it comes to language selection. I've ensured that my browser language, preferred language, and Linux locale are all set to English, and I make a point to change any settings I find in German to English as well. Despite this, some websites still display content in German.
To further prove my my point, I've just connected to a Singapore VPN, refreshed the page, and all book titles switched to English. When I disconnected from the VPN and refreshed again, the titles reverted to German.
> The problem I found with this (and many other recommendation engines) is that I've read all of the suggestions.
Immediately had the same experience: input a Theroux, Bill Bryson and Bruce Chatwin into the engine, as I've been longing for some new travel books to read, but naturally it just gave me... five or six other books by Paul Theroux and Bill Bryson.
Definitely needs more input parameters to be useful.
Reliability of ChatGPT GPT-4 isn't consistent in my experience. It seems to respond to prompts differently, but I'm not sure yet if it's based on the number of prompts in the last 8 hours or overall server load. I would guess that the API is more consistent than the ChatGPT frontend, but can't confirm for sure.
You can tune the temperature parameter and bring it to 0 (if using the API). Although technically it's not fully deterministic, it will reply with the exact same answer >99% of the time in my experience.
(This is for GPT-3 and ChatGPT. Haven't tested GPT-4)
If you've got the patience to feed all your books into librarything, the recommendations are incredible - for me virtually the whole first page are all books I've already read, but don't own.
I don't think its recommendation engine is anything sophisticated, it's just working with really really rich data.
It's got 2.8m members who have entered 186m books that they own. It cross-references those collections in some way (I don't know anything about the internals).
I just checked, and it says it's recommending a book to me (Singularity Sky) based on five other books I own (Engine City, Spin State, A Deepness In The Sky, Recursion, The Skinner). But as it's always "based on these five books", I have to assume it's doing a lot more matching than that.
That is very interesting. I think most home libraries must go deep on a few genres, rather than selecting the best from many genres. I can absolutely see how it would fail for you.
Personalized recommendation does not address that use-case. All you need to do is check reviews, lists and favorites among users on r/books or other platforms.
Psss. Please don't ruin Librarything by getting more people on there. Its recommendation algorithm is pure perfection—basically magic—and I fear it's mostly because it's only used by a very particular group of people.
My point is that recommendations that are based on social networks become less and less useful as that network grows. And LT seems to have hit the perfect size for its recommendations to be useful. I'm actively dreading the day that they either get worse (i.e. the network gets too big), or that LT goes away entirely because it has no place in the modern internet anymore, multiple times a week, to the point where I'm thinking about ways to preserve its current form in some way or another.
If more people would be on there it wouldn't be as useful too anyone anymore, instead of being as useful to more people. So instead of gatekeeping it's more like preservation of something that would otherwise vanish. Librarything is basically one of the few national parks the internet has left.
Finally, and maybe most importantly, my original comment was really meant as a light-hearted comment on the magic of LT with some of the thoughts I have on the matter sprinkled in. But I should've known that HN would interpret it in the least favorable way.
I'm also a fan of LT, but most importantly I'm a fan of spreading the wonderful feeling you get from reading. If LT's recommendation algorithm is only good because of its pool size, then it's bound to fail at some point in the future. Rather than delaying this inevitability -- which effectively sweeps the issue under the rug -- the better solution would be to ensure that their recommendations stay high-caliber regardless of scale. I'd imagine the only way to perform this test would to be for them to actually grow in scale, so they should be advertised as much as possible.
I really think it's the depth, not the breadth, that makes the recommendations work. I've been a member since 2005, and SciFi was pretty good right out of the gate. Now, everything's pretty good. If it hasn't been harmed by its growth up to this point, I honestly doubt a little more will hurt it.
Pretty solid recommendations. I picked a specific topic and chose three books that I've read about it and it recommended two other books that I have on my list, one that I have heard good things about but have decided against reading it and one that I haven't heard about and will check out.
Though as always, the problem with book recommendations is not that it's hard to find books about a specific topic, the problem is finding books that are a) good and b) different enough from other books I've read about a topic so as not to be very repetitive.
If this could solve a) I'd be very happy, though I cannot see how it would accomplish that.
The best attempt at solving this for myself was just going by book recommendations from actual people, but even that is hit or miss. Many people recommend books about a topic on which they've only read that one book and so they don't actually have anything to compare their book to. A book recommendation like that doesn't contain information about how good a book is, just if the one who read it liked it.
So in my opinion this is actually a pretty difficult problem and I'm not sure throwing an llm at it (I'm assuming that's what the ai in the title refers to) will solve it.
If you want to compare books, I've got a project for that: https://findsight.ai I use it for my learning as a PM to skip over books that just copy & paste from each other.
A related project is https://shepherd.com - but it focuses on high quality human suggestions.
Similarly, the top two suggestions for me were both sequels to books that I had selected.
Interestingly, I asked ChatGPT for recommendations based on the same list and it gave me a very similar result, including matching the top two suggestions! Coincidence? (I added a note that I was interested in finding new authors and it gave me a much better list.)
Love this. I put my three favourite books, and got out two recommendations that I already read and loved, and two ones that appear to be likely new favourites
Is it like "Given preference for A, B and C, suggest more"? One would like to understand what makes (specifically to this task) such box a good engine.
Have to considered using referral links for some of the recommended books?
I don't think that everything needs to be monetised. On the contrary - there's too much stuff existing merely to just extract value from users. But, the recommendations I've seen here look really good and I'm already ordering one of the books (the other one I've already bought).
I'm interested in old game programming books. I put in three that I have, and I got a couple modern programming book recommendations. Is there a way to add consideration for age of material?
selected three books that I love, two out of three recommended books are childrens books. Weird.. My selected books obviously were not childrens books. Maybe because I selected Dutch books?
Infinite Jest, 1984 and Moveable Feast return Catcher in the Rye, Sun Also Rises, Gravity's Rainbow and Slaughterhause-Five. These are very basic recommendations. Not great
I found that it recommended the same books that I'd get from any non-AI-powered site when I say I like "Three Body Problem", "Brave New World", and "Dune". What I'd really like is for it to help me find books I wouldn't think to try reading by asking me questions about what I enjoy in life and topics I find interesting.
Lots of book sites have recommendations. E.g. "Readers also enjoyed" on Goodreads and "People who bought this also bought" on Amazon.
They're anonymous-ish (in that you don't have to be logged on, though I'm sure tracking cookies gunna track), and they're direct, but they're only for one book at a time.
I just tried it. The look and feel is really nice. The topical search was helpful. Bookshelves are a cool idea and "lists we think you will like" in the footer was helpful when I found a list that was OK but with books that were too academic for my interests in a topic.
Book Title search seemed like it could use some kind of "not found, but..." Helper, or suggestion functionality.
I searched "Moscow Calling," "Remembered Prisoners of a Forgotten War," and "Nixon at the Movies" with no title results. Huckleberry Finn worked OK.
Would use it again though, thanks for dropping a link in the discussion.
Ya, the search is really simple and more of a browsing tool. I wanted to try something unique and get it out quickly. It is not working well; I am going to redo that more in the style of Google search. And ya I will def do something better if it is not found in the future.
We don't have those books in our system yet as no author has recommended them is why nothing is showing up. We are still pretty limited as we have interviewed 8,000 authors in different areas, but that isn't a lot in the grand scheme of books. Slowly getting in more every week :)
I'm echoing my other comment a little bit but I've been following Shepherd and thought I would comment since you're here. I like a lot of your ideas but I haven't quite managed to get recommendations that consistently sound interesting. I think it has something to do with authors and it would be interesting to know how you're thinking about how authors or writing styles are related.
For example, I like Bill Bryon and have read most everything he has written. He's good at making subjects I am not interested in captivating. For example medical history and anatomy in his book The Body.
I would love to read other books that make the uninteresting interesting but when I put The Body into Shepherd (or most recommendation engines) I mainly get other books about anatomy. This makes sense on the surface, but I've already read a book on anatomy. I'm ready for something else interesting.
I realize that might not be very actionable or useful, but when I am looking for something new to read I don't know what I am looking for. I just know the "vibes" books and authors I like, and often find that recommenders default to similar subjects only. Maybe this is difficult or impossible to capture, but it's been nagging me as something missing.
Thanks, this is super helpful! I love Bill Bryson as well :)
Yep, I totally understand what you are saying, and that is what I am working toward. It is a challenge.
Right now, I ask authors to share 5 books they love around a topic/theme/mood. So I am collecting a human grouping of books similar in some way that humans decided along with why they love it.
For example, if you like "Notes from a Small Island" or "Down Under" (two of my fav Bill Bryson books), here are books that authors have grouped with it and also loved:
So I am using human groupings to help discover books that humans associate with his work somehow. And above each book, their list title helps you understand how their mind grouped it.
For example, "Into The Wild" is associated with it based around a human grouping books that capture the spirit of Jack Kerouac's On The Road.
What do you think?
What is next to improve this?
I'll add filters to help people hone in on why they loved the book to help pull that thread out and show books along those lines. For example, if I liked Catch 22 for its absurd humor, I want to make that the common denominator on the page. Or if I like "From a Small Island" for the humor and history, picking those to try to find books with a similar book DNA.
In about 4 to 5 weeks I'll ship the first version of this on the bookshelf pages. And in maybe 12 to 16 weeks on the books-like pages, as that needs a lot more work.
And, I am hoping next year to launch Book DNA, where I pull in reader data and help line up books that are your all time favorites with others to map this out a bit further. Slowly getting there and a lot will dependon collecting more data from readers in 2024.
Nice! These "books-like" lists feel and resonate better with me. From the first list I've read Notes from a Small Island, Into the Wild, and Wild, and now some of the others on the list that I don't know, like Llama Drama, look promising. I think you're on the right track.
I like the idea of pulling as many threads out of a book to drill into why you might like something. Especially if those threads are not necessarily related to each other as that should widen the recommendation pool.
I still think there is something worth doing with author links as well. I played around with gnooks.com after someone else posted a link and within a few minutes found authors I had never heard of that had books that looked interesting.
I want to read more books like "Financial Shenanigans, Fourth Edition: How to Detect Accounting Gimmicks and Fraud in Financial Reports". However, neither the book nor the first author are listed in your database. I couldn't find any narrow topic to match either.
Yep we only have books in our system that the 8,000 authors we have done these interviews with so far loved. So we are still missing a ton of books. We are adding more every week and eventually, I bet we will find someone who loves it. I am also hoping in late 2023 and early 2024 to expand and bring in the 3 favorite books that readers read that year. So that will give us a bit more data.
I played around with something similar to what you are talking about - take your Goodreads bookshelf, see what you've read and what you have marked as "to-read" and then make a recommendation based on that. It is not perfect by any means, but would love feedback!
GPT4 is pretty good at this. Here's what I got on a first run, though you can keep prompting it to go more esoteric if you want. I honestly think that GPT4 will obsolete most existing recommendation systems; it's already better than what I previously used (Goodreads).
> Prompt: give me some books similar to "Three Body Problem", "Brave New World", and "Dune" - but dont give me the common suggestions, give me some more esoteric stuff i probably haven't heard of
> I understand that you're looking for lesser-known, yet thought-provoking science fiction novels similar to "Three Body Problem," "Brave New World," and "Dune." Here are some esoteric suggestions that you might not have heard of:
> "Blindsight" by Peter Watts - This hard sci-fi novel explores the nature of consciousness and humanity's first contact with a terrifyingly alien intelligence.
> "The Quantum Thief" by Hannu Rajaniemi - A post-human heist story set in a future Solar System, where advanced technology has given birth to an array of strange and wondrous societies.
> "The Left Hand of Darkness" by Ursula K. Le Guin - A groundbreaking work of feminist science fiction that explores gender and societal norms on a planet where inhabitants can change their sex at will.
> "The Stars My Destination" by Alfred Bester - A classic sci-fi novel that combines elements of revenge, teleportation, and corporate intrigue in a richly imagined future world.
> "The Dispossessed" by Ursula K. Le Guin - A thought-provoking tale of two societies, one anarchistic and the other capitalistic, and the physicist who attempts to bridge the divide between them.
I can vouch for the entire recommendations list (Blindsight or Quantum Thief series are my go-to answer when people say "what's your favorite book"), but I wouldn't really call them "lesser knowm" - they all won prestigious awards like Locus or Hugo.
105 comments
[ 4.4 ms ] story [ 161 ms ] threadTo further prove my my point, I've just connected to a Singapore VPN, refreshed the page, and all book titles switched to English. When I disconnected from the VPN and refreshed again, the titles reverted to German.
No details in the page, but since this submission is a "Show HN", delta234 must be the bridge...
It seems like it needs an option to thumbs up/down the responses so that the system can continue to hone in on books that are new to me.
Immediately had the same experience: input a Theroux, Bill Bryson and Bruce Chatwin into the engine, as I've been longing for some new travel books to read, but naturally it just gave me... five or six other books by Paul Theroux and Bill Bryson.
Definitely needs more input parameters to be useful.
(This is for GPT-3 and ChatGPT. Haven't tested GPT-4)
I don't think its recommendation engine is anything sophisticated, it's just working with really really rich data.
I just checked, and it says it's recommending a book to me (Singularity Sky) based on five other books I own (Engine City, Spin State, A Deepness In The Sky, Recursion, The Skinner). But as it's always "based on these five books", I have to assume it's doing a lot more matching than that.
My point is that recommendations that are based on social networks become less and less useful as that network grows. And LT seems to have hit the perfect size for its recommendations to be useful. I'm actively dreading the day that they either get worse (i.e. the network gets too big), or that LT goes away entirely because it has no place in the modern internet anymore, multiple times a week, to the point where I'm thinking about ways to preserve its current form in some way or another.
If more people would be on there it wouldn't be as useful too anyone anymore, instead of being as useful to more people. So instead of gatekeeping it's more like preservation of something that would otherwise vanish. Librarything is basically one of the few national parks the internet has left.
Finally, and maybe most importantly, my original comment was really meant as a light-hearted comment on the magic of LT with some of the thoughts I have on the matter sprinkled in. But I should've known that HN would interpret it in the least favorable way.
Though as always, the problem with book recommendations is not that it's hard to find books about a specific topic, the problem is finding books that are a) good and b) different enough from other books I've read about a topic so as not to be very repetitive.
If this could solve a) I'd be very happy, though I cannot see how it would accomplish that. The best attempt at solving this for myself was just going by book recommendations from actual people, but even that is hit or miss. Many people recommend books about a topic on which they've only read that one book and so they don't actually have anything to compare their book to. A book recommendation like that doesn't contain information about how good a book is, just if the one who read it liked it.
So in my opinion this is actually a pretty difficult problem and I'm not sure throwing an llm at it (I'm assuming that's what the ai in the title refers to) will solve it.
Still, it's a neat project.
A related project is https://shepherd.com - but it focuses on high quality human suggestions.
https://www.gnooks.com
The recommendations seem to get better with every author you rate.
https://help.goodreads.com/s/article/How-do-I-import-or-expo...
EDIT: The recommendations still feel less like AI and more like k-means clustering.
Interestingly, I asked ChatGPT for recommendations based on the same list and it gave me a very similar result, including matching the top two suggestions! Coincidence? (I added a note that I was interested in finding new authors and it gave me a much better list.)
What's the underlying algorithm?
A veteran for movie recommendations: https://movielens.org/
And how would that work?
Is it like "Given preference for A, B and C, suggest more"? One would like to understand what makes (specifically to this task) such box a good engine.
I don't think that everything needs to be monetised. On the contrary - there's too much stuff existing merely to just extract value from users. But, the recommendations I've seen here look really good and I'm already ordering one of the books (the other one I've already bought).
And in which other sites you input a list of books and get a list of recommendations?
Like this one: anonymously, directly?
They're anonymous-ish (in that you don't have to be logged on, though I'm sure tracking cookies gunna track), and they're direct, but they're only for one book at a time.
Book Title search seemed like it could use some kind of "not found, but..." Helper, or suggestion functionality.
I searched "Moscow Calling," "Remembered Prisoners of a Forgotten War," and "Nixon at the Movies" with no title results. Huckleberry Finn worked OK.
Would use it again though, thanks for dropping a link in the discussion.
We don't have those books in our system yet as no author has recommended them is why nothing is showing up. We are still pretty limited as we have interviewed 8,000 authors in different areas, but that isn't a lot in the grand scheme of books. Slowly getting in more every week :)
For example, I like Bill Bryon and have read most everything he has written. He's good at making subjects I am not interested in captivating. For example medical history and anatomy in his book The Body.
I would love to read other books that make the uninteresting interesting but when I put The Body into Shepherd (or most recommendation engines) I mainly get other books about anatomy. This makes sense on the surface, but I've already read a book on anatomy. I'm ready for something else interesting.
I realize that might not be very actionable or useful, but when I am looking for something new to read I don't know what I am looking for. I just know the "vibes" books and authors I like, and often find that recommenders default to similar subjects only. Maybe this is difficult or impossible to capture, but it's been nagging me as something missing.
Yep, I totally understand what you are saying, and that is what I am working toward. It is a challenge.
Right now, I ask authors to share 5 books they love around a topic/theme/mood. So I am collecting a human grouping of books similar in some way that humans decided along with why they love it.
For example, if you like "Notes from a Small Island" or "Down Under" (two of my fav Bill Bryson books), here are books that authors have grouped with it and also loved:
https://shepherd.com/books-like/notes-from-a-small-island https://shepherd.com/books-like/down-under
So I am using human groupings to help discover books that humans associate with his work somehow. And above each book, their list title helps you understand how their mind grouped it.
For example, "Into The Wild" is associated with it based around a human grouping books that capture the spirit of Jack Kerouac's On The Road.
What do you think?
What is next to improve this?
I'll add filters to help people hone in on why they loved the book to help pull that thread out and show books along those lines. For example, if I liked Catch 22 for its absurd humor, I want to make that the common denominator on the page. Or if I like "From a Small Island" for the humor and history, picking those to try to find books with a similar book DNA.
In about 4 to 5 weeks I'll ship the first version of this on the bookshelf pages. And in maybe 12 to 16 weeks on the books-like pages, as that needs a lot more work.
And, I am hoping next year to launch Book DNA, where I pull in reader data and help line up books that are your all time favorites with others to map this out a bit further. Slowly getting there and a lot will dependon collecting more data from readers in 2024.
I like the idea of pulling as many threads out of a book to drill into why you might like something. Especially if those threads are not necessarily related to each other as that should widen the recommendation pool.
I still think there is something worth doing with author links as well. I played around with gnooks.com after someone else posted a link and within a few minutes found authors I had never heard of that had books that looked interesting.
Yep the author links is coming as well, I've been working on some basics there.
https://www.amazon.com/Financial-Shenanigans-Fourth-Accounti...
http://portal.som.yale.edu/sites/default/files/files/MGT%208...
Ya that is harder topic, I am working on more around fraud, but here are some that might be good: https://shepherd.com/bookshelf/fraud https://shepherd.com/bookshelf/confidence-trick https://shepherd.com/bookshelf/money-laundering
In about 5 weeks I'll have filters to help you hone in from those to a specific topic.
You also might like this list on money laundering from Monica, she is a world expert on the subject and did a fascinating list on the subject: https://shepherd.com/best-books/tackling-money-laundering-ri...
https://goodreadsgpt.streamlit.app/
> Prompt: give me some books similar to "Three Body Problem", "Brave New World", and "Dune" - but dont give me the common suggestions, give me some more esoteric stuff i probably haven't heard of
> I understand that you're looking for lesser-known, yet thought-provoking science fiction novels similar to "Three Body Problem," "Brave New World," and "Dune." Here are some esoteric suggestions that you might not have heard of:
> "Blindsight" by Peter Watts - This hard sci-fi novel explores the nature of consciousness and humanity's first contact with a terrifyingly alien intelligence.
> "The Quantum Thief" by Hannu Rajaniemi - A post-human heist story set in a future Solar System, where advanced technology has given birth to an array of strange and wondrous societies.
> "The Left Hand of Darkness" by Ursula K. Le Guin - A groundbreaking work of feminist science fiction that explores gender and societal norms on a planet where inhabitants can change their sex at will.
> "The Stars My Destination" by Alfred Bester - A classic sci-fi novel that combines elements of revenge, teleportation, and corporate intrigue in a richly imagined future world.
> "The Dispossessed" by Ursula K. Le Guin - A thought-provoking tale of two societies, one anarchistic and the other capitalistic, and the physicist who attempts to bridge the divide between them.
I can import the same echo chamber anywhere I go
I want to hop dimensions, we dont have a shared reality and are coddled with a familiar soma just like in brave new world
Honestly the best I’ve seen for this are website that just let you browse YouTube and social media sites under a different users session