[Mathnerd314]

> Reply only the tags

LLM's are really sensitive to bad or even slightly ambiguous grammar. I wonder if the numbers would differ significantly with "Reply only with the tags, in the following format".

[vtuulos]

I had the same concern. However, the structure of the output was surprisingly stable. We rejected badly formatted responses: https://github.com/outerbounds/hacker-news-sentiment/blob/ma...

The semantics of the topics/tags could be improved for sure with a more detailed prompt