ContextArticle

A tag vocabulary of 1,856 entries is too large to feed to an LLM in one shot as a flat multiple-choice 'which of these tags match' prompt.

Untagged older blog content sits against an 1,856-tag vocabulary that is impractical to hand to an LLM whole and ask it which tags fit. ✦ AI generated

the author · Simon Willison's Weblog · 2026-08-14 · original ↗

Share card ↓Export .md Export .txt

I still have quite a bit of older content on my blog that I never got round to tagging. My blog has 1,856 tags - likely too many to feed to an LLM in one go and say "which of these tags match the following content".

Read full article ↗excerpt · fair-use quotation

✳ LLM ◉ Doug Turnbull

Around this claim

In practice · 1

This moment responds to

explains mechanism → Instead of classifying against a fixed tag vocabulary, let the model freely hallucinate candidate tags, then resolve them to concrete existing tags via vector embeddings over the corpus.the author · Simon Willison's Weblog