My trick for getting consistent classification from LLMs | Hacker News

There is a flaw with the base problem: each tweet only has one label, while a tweet is often about many different things and can't be delinated so cleanly. Here's an alternate approach that both allows for multiple labels and lower marginal costs (albeit higher initial cost) for each tweet classified.1. Curate a large representative subsample of tweets. 2. Feed all of them to an LLM in a single ca