New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Cost optimization with "Be Concise" instruction is not clear. #24

Open

vvv-tech opened this issue Sep 14, 2023 · 0 comments

vvv-tech commented Sep 14, 2023

Statement is: 40-90% saved with this instruction

I see that it's "Based on experimentation with GPT-3.5-Turbo using a suite of prompts on 2023-05-08."
But it's not clear

what a test suite is
what version of gpt-3.5-turbo it is (we already have 3 versions)

Interesting related link:
https://arxiv.org/pdf/2309.03409.pdf + CTRL-F + "take a deep breath"

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment