Skip to content
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.

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

Improve 4o-mini output via reasoning #12

Merged
merged 7 commits into from
Oct 31, 2024
Merged

Improve 4o-mini output via reasoning #12

merged 7 commits into from
Oct 31, 2024

Conversation

jlowin
Copy link
Owner

@jlowin jlowin commented Oct 29, 2024

This PR significantly improves GPT-4o-mini's performance with the following steps:

  • adding a separate reasoning step with a structured response over each label
  • enhancements to ControlFlow, in particular how success tool instructions are generated
  • tweaking instructions to better reflect the objective

4o-mini is now capable of handling more complex instructions like "never apply this label" (when a label is otherwise obviously appropriate) or contextual application that would fail previously and require 4o proper.

@github-actions github-actions bot added the enhancement New feature or request label Oct 29, 2024
@jlowin jlowin merged commit 3ef1ce6 into main Oct 31, 2024
1 check passed
@jlowin jlowin deleted the 4o-mini branch October 31, 2024 19:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant