Skip to content

Update prompt optimization guide with new resources #213

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update prompt optimization guide with new resources #213

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions concept-deep-dive/prompting/prompt_optimization.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,10 @@ SPO proved highly efficient and applicable to both open- and closed-ended tasks.

**Computational Cost** Manual prompt engineering is computationally cheap, but proves brittle and labor-intensive. Gradient-based tuning proves to be more compute-efficient, while RL and search-based methods are costly due to the number of required queries of the method to iterate and improve on the prompt. SPO-like approaches seem promising due to *(i)* limited number of queries and *(ii)* disuse of model internals at test-time.

# External Resources

[God Tier Prompts](https://www.godtierprompts.com) - A community driven leaderboard where the best prompts rise to the top.

### References
```bash
@article{brown2020language,
Expand Down