I just spent time getting it all running on docker compose and moved my web ui from express js to flask. I want to get the code cleaned up and open source it at some point.

I'm seeing "Thanos committing fraud" in a section about "useful lies". Given that the founder is currently in prison, it seems odd to consider the lie useful instead of harmful. It kinda seems like the AI found a bunch of loosely related things and mislabeled the group.

If you've read these books I'm not seeing what value this adds.

0. https://github.com/ValdikSS/GoodbyeDPI

Anyway, it introduced me to the idea of using computational methods in the humanities, including literature. I found it really interesting at the time!

One of the the terms it introduced me to is "distant reading", whose name mirrors that of a technique you may have studied in your gen eds if you went to university ('close reading"). The idea is that rather than zooming in on some tiny piece of text to examine very subtle or nuanced meanings, you zoom out to hundreds or thousands of texts, using computers to search them for insights that only emerge from large bodies of work as wholes. The book argued that there are likely some questions that it is only feasible to ask this way.

An old friend of mine used techniques like this for dissertation in rhetoric, learning enough Python along the way to write the code needed for the analyses she wanted to do. I thought it was pretty cool!

I imagine LLMs are probably positioned now to push distant reading forward in an number of ways: enabling new techniques, allowing old techniques to be used without writing code, and helping novices get started with writing some code. (A lot of the maintainability issues that come with LLM code generation happily don't apply to research projects like this.)

Anyway, if you're interested in other computational techniques you can use to enrich this kind of reading, you might enjoy looking into "distant reading": https://en.wikipedia.org/wiki/Distant_reading

In "Father wound" the words "abandoned at birth" are connected to "did not". Which makes it look like those visual connections are just a stylistic choice and don't carry any meaning at all.

The one I found most connected that the LLm didn’t was a connection between Jobs and the The Elephant in the Brain

The Elephant in the Brain: The less we know of our own ugly motives, the easier it is to hide them from others. Self-deception is therefore strategic, a ploy our brains use to look good while behaving badly.

Jobs: “He can deceive himself,” said Bill Atkinson. “It allowed him to con people into believing his vision, because he has personally embraced and internalized it.”

I do like the idea though — perhaps there is a way to refine the prompting to do a second pass or even multiple passes to iteratively extract themes before the linking step.

Have you read the Syntopicon by Mortimer J Adler?

It's right up your alley on this one. It's essentially this, but in 1965, by hand, with Isaac Asimov and William F Buckley Jr, among others.

Where did you get the books from? I've been trying to do something like this myself, but haven't been able to get good access to books under copyright.

Yeah, thinking a bit more here, you've created a Syntopicon. I've always wanted to make a modern one too! You can do the old school late night Wikipedia reading session with the trails idea of yours. Brilliant!

Really though, how can I help you make this bigger?

I think that this sucks the discreet joy out of reading and learning. Having the ways that the topics within a certain book can cross over in lead into another book of a different topic externalized is hollowing and I don’t find it useful.

On the other hand I feel like seeing this process externalized gives us a glimpse at how “the algorithms” (read: recommender systems) suggest seemingly disjunctive content to users. So as a technical achievement I can’t knock what you’ve done and I’m satisfied to see that you’re the guy behind the HN Book map that I thought was nice too.

At its core this looks like a representation of the advantages that LLMs can afford to the humanities. Most of us know how Rob Pike feels about them. I wonder if his senior former colleague feels the same: https://www.cs.princeton.edu/~bwk/hum307/index.html. That’s a digression, but I’d like to see some people think in public about how to reasonably use these tools in that domain.

I was recently trying to remember a portal fantasy I read as a kid. Goodreads has some impressive lists, not just "Portal Fantasies"[0], but "Portal Fantasies where the portal is on water[1], and a seven more "where/what's the portal" categories like that.

But the portal fantasy I was seeking is on the water and not on the list.

LLMs have failed me so far, as has browsing the larger portal fantasy list. So, I thought, what if I had an LLM look through a list of kids books published in the 1990s and categorize "is this a portal fantasy?" and "which category is the portal?"

I would 1. possibly find my book and 2. possibly find dozens of books I could add to the lists. (And potentially help augment other Goodread-like sites.)

Haven't done it, but I still might.

Anyway, thanks for making this. It's a really cool project!

[0] https://www.goodreads.com/list/show/103552.Portal_Fantasy_Bo...

[1] https://www.goodreads.com/list/show/172393.Fiction_Portal_is...

Edit/update: if you are looking for the phantom thread between texts, believe me that an LLM cannot achieve it. I have interrogated the most advanced models for hours, and they cannot do the task to any sort of satisfactory end that a smoked-out half-asleep college freshman could. The models don't have sufficient capacity...yet.

You have an interesting idea here, but looking over the LLM output, it's not clear what these "connections" actually mean, or if they mean anything at all.

Feeding a dataset into an LLM and getting it to output something is rather trivial. How is this particular output insightful or helpful? What specific connections gave you, the author, new insight into these works?

You correctly, and importantly point out that "LLMs are overused to summarise and underused to help us read deeper", but you published the LLM summary without explaining how the LLM helped you read deeper.

I won't pile on to what everyone else has said about the book connections / AI part of this (though I agree that part is not the really interesting or useful thing about your project) but I think a walk-through of how you approach UI design would be very interesting!

Orwelliian motives (sheer egoism, aesthetic enthusiasm, historical impulse and political purposes) are somewhat dated.

The book was really big and it got stuck in "indexing". (Possibly broke the indexer?) But thanks to the CLI integration, it was able to just iteratively grep all the info it needed out of it. I found this very amusing.

Anthropic's article on retrieval emphasizes the importance of keyword search, since they often outperform embeddings depending on the query. Their own approach is a hybrid:

https://www.anthropic.com/engineering/contextual-retrieval

It's like grabbing a half-dozen books off the library shelf, opening to a random page in each, then flit through them, kind of like a "engineering nerd book sample platter".

The visual style of linking phrases from one section to the next looks neat, but the connections don’t seem correct. There’s a link from “fictions” to “internal motives” near the top of the first link and several other links are not really obviously correct.

#1: would a larger dataset increase the depth and breadth of insight ( go to #2) #2: with the initial top 100, are there key ‘super node’ books that stand out as ones to read due the breadth they offer. Would a larger dataset identify further ‘super node’ books.

https://en.wikipedia.org/wiki/Netflix_Prize

(Are people still trying to improve upon the original winning solution?)

Solid technical execution too. Well done!

Conclusion: you find wisdom in everything if you look for it.

Wouldn't it be good if recursive Leiden and cypher was built into an embedded DB?

That's what I'm looking into with mcp-server-ladybug.

I really appreciate you mentioning this. I think this is the nature of LLMs in general. Any symbol it processes can affect its reasoning capabilities.

https://medium.com/gft-engineering/using-text-embeddings-and...

Validation is a problem here - you find relationships, but so what? Is it right.... I can't say. It is interesting though.

It's all fun and game 'till someone loses an eye/mind/even-tenuous-connection-to-reality.

Edit: I'd mention that the themes Claude finds qualify as important stuff imo. But they're all pretty grim and it's a bit problematic focusing on them for a long period. Also, they are often the grimmest spin things that are well known.

Someone called the output "egregious, obviously referential LLM dog". And someone else called this trail an example of that: https://trails.pieterma.es/trail/tempo-gradient/

What struck me when reading it was that I parachuted into that trail with zero context. So I asked an LLM to generate some surrounding context for me: this is the verbatim prompt that I just gave gpt-5.2/medium running in my own agentic harness:

> read this: https://trails.pieterma.es/trail/tempo-gradient/. then i want you to write a short essay that shows the relationship between the different quotes making sure to use each quote in the process. the narrative should help me understand the links between the different quotes in each book in context. feel free to use your own knowledge of the books and your general knowledge to make this an approachable thing. what another llm did here is cool - it found relationships between this set of quotes. now i want you to materialize them into a compelling essay that invites curiosity and teaches me something. write the essay to tempo-gradient.md and respond in chat with how you thought about the problem and whether you thought these relationships were meaningful.

This was my agent's response:

Wrote the essay to tempo-gradient.md.

How I thought about it: I treated “tempo gradient” as the shared mechanism behind all eight excerpts—mismatch in loop speed (notice → interpret → decide → act) caused by attention, infrastructure latency, organizational rigidity, system delays, stealthy manipulation, or runaway acceleration. Then I ordered the quotes from “inner time” (tennis/attention) → engineered milliseconds (HFT) → explicit doctrine (OODA) → industrial schedules (mobilization) → structural delays (Beer Game/economy) → slow covert tempo (cyber) → extreme fast tempo (AI takeoff), so each quote sets up the next.

Whether the relationships felt meaningful: yes, mostly. They’re not “the same idea” so much as the same shape appearing in different contexts—feedback delay and decision cadence determining who gets to set the terms of reality for everyone else. The only relationship that feels a bit more interpretive than direct is tennis ↔ geopolitics, but even there the bridge (“how many nows” as a controllable input to decision tempo) is surprisingly sturdy.

And this is the output: https://gist.github.com/jflam/49753b7da64a74f07e35f6e2465f1a...

Interesting... seems like it wants the keys on your system! ;)

This project, titled "Show HN: I used Claude Code to discover connections between 100 books," is an attempt to use an LLM (Claude) to perform "syntopical reading"—analyzing a library of 100 Hacker News favorite books to find thematic "trails" and connections between seemingly disparate texts. The author used CLI tools and LLM orchestration to index topics and generate these connections, aiming to move beyond simple summarization toward deeper insight.

Below are my thoughts on the project, followed by an analysis of the specific criticisms raised in the thread.

My Thoughts Conceptually, this is a fascinating experiment in "digital humanities." It attempts to automate a very high-level cognitive task: synthesis. Usually, we use computers for retrieval (search) or storage. Using them to find semantic bridges between concepts like "Jobs' reality distortion field" and "Theranos' fake demos" is a compelling use case for LLMs.

However, the execution reveals the current limits of this technology. The resulting "connections" often feel like a parlor trick—impressive that the machine did it, but often lacking the "click" of genuine insight. The project succeeds more as a technical visualization of vector embeddings than as a literary tool. It produces a map of linguistic proximity rather than conceptual necessity.

Criticisms & Agreement Analysis Here are the main criticisms from the comment section and my take on them:

1. The "Rorschach Test" / Spurious Connections Criticism: Users like tmountain, smusamashah, and timoth3y argue that the connections are "weaker than weak" or purely surface-level (e.g., linking "fracture" in one book to "crumble" in another). They suggest the project is an "LLM Rorschach test" where the human user forces meaning onto random noise generated by the model.

Do I agree? Yes. Reasoning: LLMs operate on statistical probability and vector similarity. They often confuse topical relatedness (these words appear in similar contexts) with causal or logical connection. A connection between "Us/Them" and "fictions" might make sense in a vector space, but to a human reader expecting a philosophical argument, it feels disjointed. Without the reasoning for the link being rigorous, the user has to do the heavy lifting to invent the connection, making the tool less of a "guide" and more of a "random prompt generator.”

2. Outsourcing Critical Thought Criticism: Users eloisius and DrewADesign argue that the project defeats the purpose of reading.[1] They contend that "the thinking is the point," and having a machine find connections robs the reader of the synthesis process that leads to understanding.

Do I agree? Partially. Reasoning: If the goal is learning, they are correct; you cannot learn by having a machine digest information for you. However, if the goal is discovery or research, this criticism is too harsh. Researchers have always used indices, concordances, and bibliographies to find connections they didn't know existed. If this tool is treated as a "super-index" rather than a "replacement reader," it has validity. The danger lies in mistaking the map (the AI's graph) for the territory (the actual knowledge).

3. Hallucinations and Conceptual Errors Criticism: User 8organicbits pointed out a weird label ("Thanos committing fraud" in a section about "useful lies") and questioned the logic of calling a fraud "useful" if the founder is in prison.

Do I agree? Yes. Reasoning: (Note: User Terretta clarified the commenter likely confused the comic villain Thanos with the company Theranos, which was in the text). However, the criticism about the label "useful lies" holds up. The LLM likely grouped "Theranos" under "useful lies" because the deception functioned for a time, but it lacks the nuance to understand that "fraud" and "useful tool" are categorically different to a human moral compass. This highlights the "alien" nature of LLM categorization—it organizes by semantic weight, not human logic.

4. "LLM Slop" and Fatigue Criticism: User typon and others noted the descriptions have a "distinct LLM voice" and dismissed it as "slop."[1] User Aurornis mentioned recognizing the writing style immediately.

Do I agree? Yes. Reasoning: By 2026 (the context of this thread), users are highly attuned to "AI-ese"—the perfectly grammatical but hollow, hedging, and overly enthusiastic tone of standard model outputs. This "slop" creates a trust deficit. When a human reads a connection written by a human, they assume intent. When they read one written by an LLM, they assume hallucination until proven otherwise. This high barrier to trust makes the project harder to enjoy.

Conclusion I agree with the consensus of the thread: Cool tech demo, shallow utility. The project is a great example of what LLMs can do (processing vast amounts of text to find patterns), but it inadvertently highlights what they cannot do (understand the deep, human significance of those patterns). It effectively automates the "what" but misses the "so what?"