Open darthtrevino opened 5 months ago
It could be useful to create a "prompt gym" where prompts + models + parameters can be tuned and compared against our best-performing runs. We'll need some good labeled data and the ability to measure LLM output quality.
DSPy could be interesting for that
It could be useful to create a "prompt gym" where prompts + models + parameters can be tuned and compared against our best-performing runs. We'll need some good labeled data and the ability to measure LLM output quality.