Ask HN: How does everyone keep track of user reactions to their LLM output?

2 pointsvsroy1 comment

For example: If you make a chat bot and let the user regenerate their responses; then there is an implicit preference ranking of the chatbot responses. Do any of you keep track of this?

View on HN

On ChatGPT you can give feedback. Also there is a sort of upvote checkmark thing that I think helps them gauge good response patterns to feed back into their updated versions.

Reply on news.ycombinator.com