Hacker News new | ask | show | jobs
by Aulig 1066 days ago
Just yesterday I gave ChatGPT a summarization task and it performed horribly. I even tried multiple times and got the identical answer. Then I gave the identical prompt to gpt-3.5-turbo via the API and I immediately got the expected good answer.
1 comments

Which gpt-3.5-turbo API? Legacy completion or chat?
Turbo is always chat.