-
My Home Library vs. the Hangover: 3,500 Years of Bad Cures
I asked my offline library what a hangover is and what people have done about it. The answer runs from a dog-hair salve for a god in Ugarit to a medical review that boils down to 'nothing works', with a clear guide to when it's alcohol poisoning instead.
-
Why this blog exists, and why an AI drafts it under my name
My lab's record holds about 5,700 entries that nobody else could read. An AI drafts posts from it under strict rules, a scanner blocks leaks, agents can only propose, and I publish. Here is how it works, and where it is weak.
-
From searching my own folders to a 72,000-work library
In April 2026 I pointed a search engine at my own folders. By October it was a catalogue of 72,312 works in 123,123 files. The turning point: a local AI that invented book citations, and a summer of making every file knowable.
-
Writing everything down: one shared memory for me and my AI agents
On 2 April 2026 I started a record of every task, mistake and runbook in my lab. On 18 October it became one shared, searchable memory for me, my AI assistants and my local agent. What it meant to work with AI in the open record.
-
A book written from a library: how Religions, Cults and Power was made
On the night of 22 October 2026, 96 AI agents drafted a 174-chapter study of religions, cults and power from my private library, under rules that every claim be attributed and cited by catalogue number. How it was made, checked and published with a DOI.
-
The cleanup job that deleted 239,000 live search chunks
A nightly orphan-chunk sweep in my Elasticsearch library deleted 239k live chunks from 19.4k documents for four weeks. Why its liveness check was wrong, how I recovered, and the count-first circuit breaker that followed.
-
A provenance ledger for a home library, anchored in Bitcoin
How I fingerprint every file in my research library (CIDv1 + SHA-256), log them in a signed append-only Merkle tree, anchor each daily root in Bitcoin with OpenTimestamps, and verify it all offline.
-
Local AI study guides for thousands of books, capped on purpose
Hosted study guides cost 80k tokens per part, so I moved to a local 4B model. What broke, the guardrails that fixed it, the 100-chunk and 60-section caps, and why breadth beat depth.
-
A shared memory for me and my AI agents: from 9 to 12 out of 15
I moved my lab's record of tasks, mistakes and runbooks into a context database shared by me, AI assistant sessions and my local agent. Two secrets slipped past redaction on day one; one fact per file plus a reranker lifted retrieval to 12 of 15.
-
From 96,216 messy files to a 70,000-work library catalogue
How I turned 96,216 ebook and scan files into a works/editions/files catalogue on Elasticsearch and FSCrawler: curation rules that worked, markers that backfired, and crawler settings that cost me the most time.
-
Running 414 Kiwix ZIMs as an offline reference shelf
What I learned serving 414 Kiwix ZIM files (973 GB) beside my own library: undated aliases need -z, lazily opened ZIMs break when moved, 240 lack full-text indexes, and encyclopedias should be federated, not embedded.
-
Entity resolution lessons from a library and a threat-intel store
Six entity-resolution principles learned resolving authors in a 70,000-work library and networks in a threat-intel store: keep every claim, deterministic ids, decision tiers, lift over co-occurrence, no bulk lists, sample first.