Comment

Comment by tungle

Hi, thanks for trying out. OpenAI just limit the whole prompt to 4096 token (that's around 2,000 words), so I have to limit each answer. I tried hacking by adding summarization for the first part of the convo, then chat along as normal, but the result wasn't that great. Will tweak more.
parent tungle 3 years ago

No comments yet

Be the first to share your thoughts.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton