🦄 ai that works: Prompt Optimization
🦄 ai that works
A weekly conversation about how we can all get the most juice out of todays models with @vaibcode & @dexhorthy
https://github.com/ai-that-works/ai-that-works
No one wants to write prompts, and we all want systems that "just work". GEPA and DSPy have taken the internet by storm with attempts at making this promise.
The question remains, does this work for real problems? We'll dive deep and explain:
What is GEPA? and how is it different than DSPy?
How does one use it?
What are realistic expectations to set accordingly?
Pre-reading
To prevent repeating the basics, we recommend you come in having already understanding some of the tooling we will be using:
Discord
Cursor or VS Code
Programming languages
Application Logic: Python or Typescript or Go
Prompting: BAML (recommend video)
Meet the Speaker 🧑💻
Meet Vaibhav Gupta, one of the creators of BAML and YC alum. He spent 10 years in AI performance optimization at places like Google, Microsoft, and D. E. Shaw. He loves diving deep and chatting about anything related to Gen AI and Computer Vision!
Meet Dex Horthy, founder at HumanLayer and coiner of the term Context Engineering. He spent 10+ years building devops tools at Replicated, Sprout Social and JPL. DevOps junkie turned AI Engineer.