Hacker News Reader

> e.g. sentiment analysis when the user begins cursing at the agent, or checking whether the user continued another session with the generated code, or started a new session with the same starting point as before, i.e. they git-stashed.

Thank you for elaborating, that's already useful. Anywhere I can learn more about this? I'm very interested in it!

View on HN

To learn about sentiment analysis, I'd look for related datasets and then look at recent code, e.g. here: https://www.kaggle.com/datasets?search=sentiment+analysis

For more LLM-specific stuff, you can pick some agent trace dataset on https://huggingface.co/datasets?format=format%3Aagent-traces and check out what people are doing with it (usually linked on the right when you click on a dataset).

And of course https://scholar.google.com/ for research papers.

Reply on news.ycombinator.com