[HN Gopher] Show HN: I used Claude Code to discover connections ...
___________________________________________________________________
Show HN: I used Claude Code to discover connections between 100
books
I think LLMs are overused to summarise and underused to help us
read deeper. I built a system for Claude Code to browse 100 non-
fiction books and find interesting connections between them. I
started out with a pipeline in stages, chaining together LLM calls
to build up a context of the library. I was mainly getting back the
insight that I was baking into the prompts, and the results weren't
particularly surprising. On a whim, I gave CC access to my debug
CLI tools and found that it wiped the floor with that approach. It
gave actually interesting results and required very little
orchestration in comparison. One of my favourite trail of excerpts
goes from Jobs' reality distortion field to Theranos' fake demos,
to Thiel on startup cults, to Hoffer on mass movement charlatans
(https://trails.pieterma.es/trail/useful-lies/). A fun tendency is
that Claude kept getting distracted by topics of secrecy,
conspiracy, and hidden systems - as if the task itself summoned a
Foucault's Pendulum mindset. Details: * The books are picked from
HN's favourites (which I collected before:
https://hnbooks.pieterma.es/). * Chunks are indexed by topic using
Gemini Flash Lite. The whole library cost about PS10. * Topics are
organised into a tree structure using recursive Leiden partitioning
and LLM labels. This gives a high-level sense of the themes. *
There are several ways to browse. The most useful are embedding
similarity, topic tree siblings, and topics cooccurring within a
chunk window. * Everything is stored in SQLite and manipulated
using a set of CLI tools. I wrote more about the process here:
https://pieterma.es/syntopic-reading-claude/ I'm curious if this
way of reading resonates for anyone else - LLM-mediated or not.
Author : pmaze
Score : 125 points
Date : 2026-01-10 16:56 UTC (6 hours ago)
(HTM) web link (trails.pieterma.es)
(TXT) w3m dump (trails.pieterma.es)
| Aurornis wrote:
| It's interesting how many of the descriptions have a distinct
| LLM-style voice. Even if you hadn't posted how it was generated I
| would have immediately recognized many of the motifs and patterns
| as LLM writing style.
|
| 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.
| pmaze wrote:
| The names & descriptions definitely have that distinct LLM
| flavour to them, regardless of which model I used. I decided to
| keep them, but as short as possible. In general, I find the
| recombination of human-written text to be the main interest.
|
| There's two stages to the linking: first juxtaposing the
| excerpts, then finding and linking key phrases within them. I
| find the excerpts themselves often have interesting connections
| between them, but the key phrases can be a bit out there. The
| "fictions" to "internal motives" one does gel for me, given the
| theme of deceiving ourselves about our own motivations.
| reedf1 wrote:
| Well even the post itself reads to me as AI generated
| wormpilled wrote:
| >A fun tendency is that Claude kept getting distracted by topics
| of secrecy, conspiracy, and hidden systems
|
| Interesting... seems like it wants the keys on your system! ;)
| napolux wrote:
| Monetize it!
| joe_the_user wrote:
| _A fun tendency is that Claude kept getting distracted by topics
| of secrecy, conspiracy, and hidden systems - as if the task
| itself summoned a Foucault's Pendulum mindset._
|
| 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.
| theturtletalks wrote:
| In a similar vein, I've been using Claude Code to "read" Github
| projects I have no business understanding. I found this one
| trending on Github with everything in Russian and went down the
| rabbit hole of deep packet inspection[0].
|
| 0. https://github.com/ValdikSS/GoodbyeDPI
| dinkleberg wrote:
| That's a cool idea. There are so many interesting projects on
| GitHub that are incomprehensible without a ton of domain
| context.
| theturtletalks wrote:
| I got the idea from an old post on here called Story of
| Mel[0] where OP talks about the beauty of Mel's intricate
| machine code on a RPC-4000.
|
| This is the part that always stuck with me:
|
| I have often felt that programming is an art form, whose real
| value can only be appreciated by another versed in the same
| arcane art; there are lovely gems and brilliant coups hidden
| from human view and admiration, sometimes forever, by the
| very nature of the process. You can learn a lot about an
| individual just by reading through his code, even in
| hexadecimal. Mel was, I think, an unsung genius.
|
| 0. http://catb.org/esr/jargon/html/story-of-mel.html
| smusamashah wrote:
| I dont understand the lines connecting two pieces of text. In
| most cases, the connected words have absolutely zero connection
| with each other.
|
| 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.
| Oras wrote:
| I had the exact same impression.
| pxc wrote:
| I read a book maybe a decade ago on the "digital humanities". I
| wish now I could remember the title and author. :(
|
| 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
| plutokras wrote:
| > I wish now I could remember the title and author.
|
| LLMs are great at finding media by vague descriptions. ;)
| ako wrote:
| According to Claude (easy guess from the wikipedia link?):
|
| The book is almost certainly by *Franco Moretti*, who coined
| the term "distant reading." Given the timeframe ("maybe a
| decade ago") and the description, it's most likely one of
| these two:
|
| 1. *"Distant Reading"* (2013) -- A collection of Moretti's
| essays that directly takes the concept as its title. This
| would fit well with "about a decade ago."
|
| 2. *"Graphs, Maps, Trees: Abstract Models for Literary
| History"* (2005) -- His earlier and very influential work
| that laid out the quantitative, computational approach to
| literary analysis, even if it didn't use "distant reading" as
| prominently in the title.
|
| Moretti, who founded the Stanford Literary Lab, was the major
| proponent of the idea that we should analyze literature not
| just through careful reading of individual canonical texts,
| but through large-scale computational analysis of hundreds or
| thousands of works--looking at trends in genre evolution,
| plot structures, title lengths, and other patterns that only
| emerge at scale.
|
| Given that the commenter specifically remembers learning the
| term "distant reading" from the book, my best guess is
| *"Distant Reading" (2013)*, though "Graphs, Maps, Trees" is
| also a strong possibility if their memory of "a decade" is
| approximate.
| durch wrote:
| The insight that LLMs are "overused to summarise and underused to
| help us read deeper" gets at something fundamental. Most
| workflows treat LLMs as generators: give me an answer. But the
| real leverage is exploration: fan out, surface connections, then
| let us recognize what's worth depth.
|
| That recognition step is where the value lives. You see a
| connection, feel "yes, more of that" or "no, not quite," and
| refine. The LLM expands the search space. Our judgment prunes it.
| Each cycle sharpens understanding. Without that loop, you're just
| accepting the first output.
| glemion43 wrote:
| I'm carrying a thought around for the last few weeks:
|
| A LLM is a transformer. It transforms a prompt into a result.
|
| Or a human idea into a concrete java implementation.
|
| Currently I'm exploring what unexpected or curious
| transformations LLMs are capable of but haven't found much yet.
|
| At least I myself was surprised that an LLM can transform a
| description of something into an IMG by transforming it into a
| SVG.
| durch wrote:
| Format conversions (text - code, description - SVG) are the
| transformations most reach for first. To me the interesting
| ones are cognitive: your vague sense - something concrete you
| can react to - refined understanding. The LLM gives you an
| artifact to recognize against. That recognition ("yes, more
| of that" or "no, not quite") is where understanding actually
| shifts. Each cycle sharpens what you're looking for, a bit
| like a flywheel, each feeds into the next one.
| calmoo wrote:
| Ironically your comment is clearly written by an LLM.
| durch wrote:
| Ironic indeed: pattern-matching the prose style instead of
| engaging the idea is exactly the shallow reading the post is
| about.
| calmoo wrote:
| Your original comment is completely void of any substance
| or originality. Please don't fill the web with robot slop
| and use your own voice. We both know what you're doing
| here.
| afro88 wrote:
| LLMs are generators, and that was the correct way to view them
| at the start. Agents explore.
| durch wrote:
| Generator vs. explorer is a useful distinction, but it's
| incomplete. Agents without a recognition loop are just
| generators with extra steps.
|
| What makes exploration valuable is the cycle: act, observe,
| recognize whether you're closer to what you wanted, then
| refine. Without that recognition ("closer" or "drifting"),
| you're exploring blind.
|
| Context is what lets the loop close. You need enough of it to
| judge the outcome. I think that real shift isn't generators -
| agents. It's one-shot output - iterative refinement with
| judgment in the loop.
| throwawaySimon wrote:
| Please stop.
| durch wrote:
| Something in there you'd like to discuss further, I've
| been thinking a lot about these ideas ever since LLMs
| came around, and I think these are many more of these
| discussion ahead of us...
| dangoodmanUT wrote:
| The UI animations are so fun
| hising wrote:
| Yeah, I had a similar idea, I used Open AI API to break down
| movies into the 3 act structure, narrative, pacing, character
| arcs etc and then trying to find movies that are similar using
| PostgreSQL with pgvector. The idea was to have another way to
| find movies I would like to watch next based on more than
| "similar movies" in IMDb. Threw some hours at it, but I guess it
| is a system that needs a lot of data, a lot of tokens and
| enormous amount of tweaking to be useful. I love your idea! I
| agree with you on that we could use LLM:s for this kind of stuff
| that we as humans are quite bad at.
| lkbm wrote:
| Earlier today, I was thinking about doing something somewhat
| similar to this.
|
| 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...
| andy99 wrote:
| Would be cool to see this on fiction books instead of what seems
| like tech bro self help books mostly (I understand this is HN
| favorites but I know HN also likes Russian literature and
| Stanislaw Lem and Cyberpunk). There's the whole think about how
| there are really only N different story plots, it could be
| applied there.
| amadeuswoo wrote:
| The feedback loop you describe--watching Claude's logs, then just
| asking it what functionality it wished it had--feels like an
| underexplored pattern. Did you find its suggestions converged
| toward a stable toolset, or did it keep wanting new capabilities
| as the trails got more sophisticated?
| pmaze wrote:
| I ended up judging where to draw the line. Its initial
| suggestions were genuinely useful and focused on making the
| basic tool use more efficient. e.g. complaining about a missing
| CLI parameter that I'd neglected to add for a specific command,
| requesting to let it navigate the topic tree in ways I hadn't
| considered, or new definitions for related topics. After a
| couple iterations the low hanging fruit was exhausted, and its
| suggestions started spiralling out beyond what I thought would
| pay off (like training custom embeddings). As long as I kept
| asking it for new ideas, it would come up with something, but
| with rapidly diminishing returns.
| samuelknight wrote:
| I do this all the time in my Claude code workflow: - Claude
| will stumble a few times before figuring out how to do part of
| a complex task - I will ask it to explain what it was trying to
| do, how it eventually solved it, and what was missing from its
| environment. - Trivial pointers go into the CLAUDE.md. Complex
| tasks go into a new project skill or a helper script
|
| This is the best way to re-enforce a copilot because models are
| pretty smart most of the time and I can correct the cases where
| it stumbles with minimal cognitive effort. Over time I find
| more and more tasks are solved by agent intelligence or these
| happy path hints. As primitive as it is, CLAUDE.md is the best
| we have for long-term adaptive memory.
| timoth3y wrote:
| What meaningful connections did it uncover?
|
| 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.
| rjh29 wrote:
| 100 books is too small a datasize - particularly given it's a
| set of HN recommendations (i.e. a very narrow and specific
| subset of books). A larger set would probably draw more
| surprising and interesting groupings.
| 8organicbits wrote:
| Can someone break this down for me?
|
| 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.
| Closi wrote:
| I guess the lies were useful until she got caught?
| urbandw311er wrote:
| This feels like a nice idea but the connection between the theme
| and the overarching arc of each book seems tenuous at best. In
| some cases it just seems to have found one paragraph from
| thousands and extrapolated a theme that doesn't really thread
| through the greater piece.
|
| 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.
| amelius wrote:
| Makes me wonder, how well could an LLM-based solution score on
| the Netflix prize?
|
| https://en.wikipedia.org/wiki/Netflix_Prize
|
| (Are people still trying to improve upon the original winning
| solution?)
| bonkusbingus wrote:
| "There are, you see, two ways of reading a book: you either see
| it as a box with something inside and start looking for what it
| signifies, and then if you're even more perverse or depraved you
| set off after signifiers. And you treat the next book like a box
| contained in the first or containing it. And you annotate and
| interpret and question, and write a book about the book, and so
| on and on. Or there's the other way: you see the book as a little
| non-signifying machine, and the only question is "Does it work,
| and how does it work?" How does it work for you? If it doesn't
| work, if nothing comes through, you try another book. This second
| way of reading's intensive: something comes through or it
| doesn't. There's nothing to explain, nothing to understand,
| nothing to interpret." -- Gilles Deleuze
| tolerance wrote:
| I don't like this product as a service to readers (i.e., people
| who read as a cognitive/philosophical exploit) but I do think
| that somewhere embedded in its backend there are things of
| benefit.
|
| 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.
| mathgeek wrote:
| > 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.
|
| Intuitively, I agree. This feels like the different between
| being a creator (of your own thoughts as inspired by another
| person's) and a consumer (although in a somewhat educational
| sense). There would need to be a big advantage to being taught
| those initial thoughts, analogous to why we teach folks
| algebra/calculus via formulas rather than having every student
| figure out proofs for themselves.
| sciences44 wrote:
| Love the originality here - makes you curious to explore more.
|
| Solid technical execution too. Well done!
| jereees wrote:
| now do this for research papers! fun stuff :)
___________________________________________________________________
(page generated 2026-01-10 23:00 UTC)