The working archive · since 1999

Forty essays, twenty-six years, one continuous thread.

From AltaVista keyword density to LLM citation behaviour. The full archive of published research, in reverse chronological order. The work itself is the point.

40
Published essays
3
Volumes
~700
In the wider archive
2/wk
New since May 2026
III
Volume III · current · 2025 → 2026

Generative retrieval & statement-level visibility.

The substrate shifted. We rebuild the framework from the ground up — claim-level scoring, LLM citation behaviour, applied measurement.

Current · 10 essays
Essay 04

Statement-level visibility, or: why ranking a page no longer matters.

The unit of competition has shifted. LLM-driven retrieval doesn't surface URLs — it surfaces claims. We propose a measurement framework.

GEOretrieval
May 2026
17 min
★ this week
Essay 03

A taxonomy of LLM citation behavior across 14 frontier models.

What gets cited, what gets paraphrased, what disappears. A controlled audit across GPT-4o, Claude, Gemini, and 11 others.

AI Searchmethodology
May 2026
22 min
Essay 02

GEO is not SEO with prompts. A position paper.

The framing of GEO as 'prompt-optimized SEO' mistakes the surface for the substrate. Generative engine optimization is a distinct discipline.

GEOposition
May 2026
14 min
Essay 01

Ranking ≠ retrieval ≠ generation. A decomposition.

Three operations, often conflated. We separate them with notation, examples, and applied measurement.

foundationsresearch
Apr 2026
19 min
Essay 05

How LLMs read right-to-left: retrieval in Hebrew and Arabic.

Legacy crawlers tokenised RTL text differently than transformers embed it. The gap is now a visibility risk — and an opportunity.

RTLAI Search
Apr 2026
16 min
Essay 06

Entity disambiguation, for humans who share a name.

A model that cannot tell you apart from a stranger will average you together. The fix is structural, not editorial.

entitiesGEO
Apr 2026
15 min
Essay 07

Chunking is the new pagination.

How your document is split into retrieval chunks now determines whether its claims survive with their context intact.

retrievaltechnical
Mar 2026
14 min
Essay 08

Reproducibility as a ranking signal.

A claim that reappears across runs and paraphrases is treated as more trustworthy. Consistency is now optimisable.

methodologyGEO
Mar 2026
16 min
Essay 11

Against the prompt as product.

Selling 'prompt packs' as a GEO strategy confuses the input you control with the system you don't.

GEOposition
Feb 2026
13 min
Essay 12

Measurement, not advice.

The industry has no shortage of opinion about AI search. It has a severe shortage of controlled measurement. This archive picks a side.

methodologymanifesto
Feb 2026
10 min