Reading across books with Claude Code • Hacker News Board

Re: Reading across books with Claude Code

#31

Post by mpalmer » Sat, Jan 17, 2026, 1:25 PM UTC

lloydatkinson wrote: post #30

How can anyone even trust crap like this? It was only a few days ago Claude and ChatGPT hallucinated a bunch of stuff from actual docs I sent them links to. When asked about it, they just apologised.

Synthesizing 500 words at a time into digestible topics is significantly less prone to error. You're giving it a lot of info and asking for an organized subset. It's good at following such direction.

In your example, you're doing the inverse (give me a lot of text based on a little), and that's where LLMs have no problem hallucinating the new information.

Re: Reading across books with Claude Code

#32

Post by zkmon » Sat, Jan 17, 2026, 1:48 PM UTC

I used AI for accelerating my reading a book recently. This is a interesting usecase. But it same as racing for the destination instead enjoying the journey.

It kills the tone, pace and the expressions of the author. It is pretty much same as an assistant summarizing the whole book for you, if that's what you want. It misses the entire experience delivered by the author.

Re: Reading across books with Claude Code

#33

Post by alansaber » Sat, Jan 17, 2026, 2:00 PM UTC

jszymborski wrote: post #2

This is all interesting, however I find myself most interested in how the topic tree is created. It seems super useful for lots of things. Anyone can point me to something similar with details? EDIT: Whoops, I found more details at the very end of the article.

He asks g2.5 flash to assign a topic. I am also interested in the best way to develop a general schema- there is a good deal of literature on this but nothing stands out, I think the standard approach is open ended classification generation using a single model then binning. Actually the novelty in his approach is first asking if a chunk is useful (ie adding a filter for non-semantic information) which I would normally do at the dataset creation stage.

Re: Reading across books with Claude Code

#34

Post by alansaber » Sat, Jan 17, 2026, 2:02 PM UTC

zkmon wrote: post #32

I used AI for accelerating my reading a book recently. This is a interesting usecase. But it same as racing for the destination instead enjoying the journey. It kills the tone, pace and the expressions of the author. It is pretty much same as an assistant summarizing the whole book for you, if that's what you want. It misses the entire experience delivered by the author.

Yes AI subsumes edge cases to produce a very uniform optimal writing (what we call AI slop). I am assuming this is a book you were reading for knowledge work, not for fun? Not heard about people recreationally using AI for consumer content that's a bridge too far for me lol.

Re: Reading across books with Claude Code

#35

Post by alansaber » Sat, Jan 17, 2026, 2:03 PM UTC

padolsey wrote: post #29

Ronsenshi wrote: post #24

For me this looks like a great way to build connections between books in order to create a recommendation engine - something better than what Goodreads & Co provides. Something actually useful. The cost of indexing using third party API is extremely high, however. This might work out well with an open source model and a cluster of raspberry pi for large library indexing?

The incumbants Goodreads and their owner Amazon have indeed done such a poor job at this. Seven years ago I tried creating a basic graph using collaborative-filtering (effectively using our actual reading patterns as the embeddings space instead of semantics [human X likes book Y so likers of Y might like other things that human X has enjoyed]). It works well to this day (ablf.io) but the codebase is so ugly I've not…

Yes imo this is very useful but there's not a clear industry standard on how to do so yet, which I imagine will change? Tell me if i'm missing something

Re: Reading across books with Claude Code

#36

Post by alansaber » Sat, Jan 17, 2026, 2:04 PM UTC

mpalmer wrote: post #31

lloydatkinson wrote: post #30

How can anyone even trust crap like this? It was only a few days ago Claude and ChatGPT hallucinated a bunch of stuff from actual docs I sent them links to. When asked about it, they just apologised.

Synthesizing 500 words at a time into digestible topics is significantly less prone to error. You're giving it a lot of info and asking for an organized subset. It's good at following such direction. In your example, you're doing the inverse (give me a lot of text based on a little), and that's where LLMs have no problem hallucinating the new information.

Exactly the more tightly scoped the problem the less stochastic noise. Even better if you can add more signals based on deterministic algorithms like keyword presence etc. It gets very domain-specific very fast

Re: Reading across books with Claude Code

#37

Post by alansaber » Sat, Jan 17, 2026, 2:05 PM UTC

kylehotchkiss wrote: post #5

In several years, IMO the most interesting people are going to be the ones still actually reading paper books and not trying to shove everything into a LLM

I can't wait to have the LLM autopilot my neuralink whilst i'm in VR mario kart.

Re: Reading across books with Claude Code

#38

Post by CuriouslyC » Sat, Jan 17, 2026, 2:09 PM UTC

alansaber wrote: post #34

zkmon wrote: post #32

I used AI for accelerating my reading a book recently. This is a interesting usecase. But it same as racing for the destination instead enjoying the journey. It kills the tone, pace and the expressions of the author. It is pretty much same as an assistant summarizing the whole book for you, if that's what you want. It misses the entire experience delivered by the author.

Yes AI subsumes edge cases to produce a very uniform optimal writing (what we call AI slop). I am assuming this is a book you were reading for knowledge work, not for fun? Not heard about people recreationally using AI for consumer content that's a bridge too far for me lol.

It's not optimal. It's overwritten, repetitive, cliche and increasingly incoherent over longer generations. I say this as someone who likes AI and uses it to create rough drafts and structural revisions of my ideas.

Re: Reading across books with Claude Code

#39

Post by fatherwavelet » Sat, Jan 17, 2026, 2:16 PM UTC

kylehotchkiss wrote: post #5

In several years, IMO the most interesting people are going to be the ones still actually reading paper books and not trying to shove everything into a LLM

I still read a lot of books and I use LLMs all the time. I have even got a bunch of book recommendations from LLMs. Imagine that. You actually have agency over these tools. I know it is hard to believe for some.

Re: Reading across books with Claude Code

#40

Post by alansaber » Sat, Jan 17, 2026, 2:35 PM UTC

CuriouslyC wrote: post #38

alansaber wrote: post #34

Earlier quoted context omitted.

Yes AI subsumes edge cases to produce a very uniform optimal writing (what we call AI slop). I am assuming this is a book you were reading for knowledge work, not for fun? Not heard about people recreationally using AI for consumer content that's a bridge too far for me lol.

It's not optimal. It's overwritten, repetitive, cliche and increasingly incoherent over longer generations. I say this as someone who likes AI and uses it to create rough drafts and structural revisions of my ideas.

Exactly stochastic but statistically optimal based on a bunch of very broad range of text which often is not actually good writing