If you disregard the "DSPy is my favorite hammer and every LLM workflow project is a nail" theme, this blogpost paints a good picture of the natural evolution of LLM engineering at startups with a generative AI product:

https://skylarbpayne.com/posts/dspy-engineering-patterns/

#llms #genai #dspy

If DSPy is So Great, Why Isn't Anyone Using It?

Any sufficiently complicated AI system contains an ad hoc, informally-specified, bug-ridden implementation of half of DSPy.

Skylar Payne

The related top HN comment is also worth reading: https://news.ycombinator.com/item?id=47491023

"You're comparing [DSPy] downloads with Langchain, probably the worst package to gain popularity of the last decade. It was just first to market, then after a short while most realized it's horrifically architected, and now it's just coasting on former name recognition while everyone who needs to get shit done uses something lighter like the above two."

Preach! 🙌

#dspy #langchain #hackernews #genai #llms

I don't see it at all. > Typed I/O for every LLM call. Use Pydantic. Define what... | Hacker News