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

[Notes] Feedback from 2023-11-14 #8

Closed
psaegert opened this issue Nov 14, 2023 · 1 comment
Closed

[Notes] Feedback from 2023-11-14 #8

psaegert opened this issue Nov 14, 2023 · 1 comment

Comments

@psaegert
Copy link
Collaborator

psaegert commented Nov 14, 2023

TL;DR:

  • Implement an automatic evaluation pipeline.
  • Fine-tune GPT-3.5.

Key Concepts:

  • Analyze examples to identify patterns and ensure balance in addressing them.
  • Assess which errors are most significant for developers and which are easier to fix.
  • Note the frequency of incorrect API calls and evaluate the time-saving potential versus practical approaches.
  • Emphasize a demand versus feasibility analysis.
  • Use examples as the primary method of explanation.

Presentation Strategy:

  • Timeline in months rather than weeks.
  • Avoid the pyramid principle if the concept is complex.
  • Condense the recap to 20 seconds, focusing on core content.
  • Present the most crucial points first and allocate more time to them.
@psaegert
Copy link
Collaborator Author

Continued in #6, #12

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant