Don't classify. Hallucinate!
- Source
- simonwillison.net
- Date
- embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
It turns an oversized label set from a problem into an lookup, which is directly reusable by anyone classifying against a taxonomy too large to fit in a prompt.
“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".”
“Doug Turnbull has a neat solution. Tell the model to output tags without any details of the existing vocabulary, then use vector embeddings against the existing corpus to find the concrete tags that are closest to the ones the model imagined might fit!”
“His example prompt suggests including an example of the shape of your tags to help the model make a more useful guess”
Checking sign-in…
Loading comments…