I used Claude Code to discover connections between 100 books
Details
- External ID
- 46567400
- Source
- HN
- Company
- —
- Product
- I used Claude Code to discover connections between 100 books
- Website domain
- pieterma.es
- Launched
- Jan. 10, 2026
- Cohort
- —
- Upvotes
- 524
- Upvotes percentile
- 0.994729907773386
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
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 £10.* 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.
Enrichment
- Theme
- utilities for Claude and Claude Code
- Vertical
- Media & entertainment
- Function
- Agent / copilot
- Audience
- B2C
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- ai-powered book connection discovery
- Manually corrected
- False
Could you build this?
Yes This is an exploration project combining text processing scripts, embeddings/LLM calls, and a static Astro website to display book connections.
Discussion
20 comments analyzed.
Competitors mentioned: Readwise Reader, Neo4J visualization tools, Context Graphs
Concerns raised: LLM-generated connections lack merit compared to human-discovered ones, Results don't make sense and connections are tenuous, Trivial and uninspiring outputs, Quality concerns with LLM analysis versus human reading/interpretation, Ignores what makes human thinking valuable
Feature requests: Process and cluster References in non-fiction books instead of LLM connections, Cheaper embedding-based clustering alternative to LLM construction, Generate multiple alternative connection options to avoid bias, Include human-written TL;DR summaries after reading books yourself
Competitors
Other products that read as similar to this one — 230 launches clear the similarity bar, closest 8 shown.
Attention rank: #3 of 231 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 68 days after the earliest competitor.
- Visualizing How Books Reference Each Other Across 3k Years · hn · 2026-02-11 · 5 upvotes · similarity 0.58
- I built "AI Wattpad" to eval LLMs on fiction · hn · 2026-02-03 · 32 upvotes · similarity 0.49
- Use Claude Code to Query 600 GB Indexes over Hacker News, ArXiv, etc. · hn · 2025-12-31 · 397 upvotes · similarity 0.47
- Coffeetable, A new UX to discover books inside Claude · hn · 2026-08-25 · 15 upvotes · similarity 0.47
- I scraped 3B Goodreads reviews to train a better recommendation model · hn · 2025-11-05 · 606 upvotes · similarity 0.46
- How LLMs Work · hn · 2026-04-24 · 245 upvotes · similarity 0.46
- Alumnium · hn · 2026-03-27 · 6 upvotes · similarity 0.45
- Read while you listen to your Audiobooks · hn · 2026-09-26 · 5 upvotes · similarity 0.44
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.