3 Comments
User's avatar
Tom Haymes's avatar

I like to say, "we shouldn't look to AI for answers, we should look to it for questions."

Expand full comment
Gerben Wierda's avatar

With on-the-fly adding search to the context, the LLMs indeed turn into 'fancy search'. It's an insightful perspective.

Made me muse about telling the AI 'not to use social media' as part of the context for the 'fancy' part.

PS. Your reporting on real world experiments with prompts have been pretty interesting.

Expand full comment
Gerben Wierda's avatar

Adding to this: it's a bit 'search with LLM-summarising on top'. And summarising by LLMs is a tug of war between parameters and context, depending on the subject one may get more of the one or the other (see https://ea.rna.nl/2024/05/27/when-chatgpt-summarises-it-actually-does-nothing-of-the-kind/ for my experiment a while back)

Expand full comment