[okhat]

Very cool! But for hard enough problems, prompt engineering is kind of like hyperparameter tuning. It's only a final (and relatively minor) step after building up an effective architecture and getting its modules to work together.

DSP provides a high-level abstraction for building these architectures—with LMs and search. And it gets the modules working together on your behalf (e.g., it annotates few-shot demonstrations for LM calls automatically).

Once you're happy with things, it can compile your DSP program into a tiny LM that's a lot cheaper to work with.

https://github.com/stanfordnlp/dsp/

[Khelavaster]

Prompt engineering is close to training data curation for ResNets. Way beyond hyperparameter tuning.

[muggermuch]

This looks extremely useful! Thanks a ton.