Bay.Area.AI: DSPy: Prompt Optimization for LM Programs, Michael Ryan

This talk video is a node in devreal.ai, the developer community graph. It connects to: Talk: DSPy: Prompt Optimization for LM Programs — https://devreal.ai/t/240912-dspy-prom... Interview: Bay.Area.AI: Interview with Michael Ryan, Stanford — https://devreal.ai/t/240912-bay-area-... Speaker: Michael Ryan — https://devreal.ai/n/michael-ryan Company: Stanford University — https://devreal.ai/c/stanford-university Project: DSPy — https://devreal.ai/p/dspy Event: DSPy and GraphRAG: Making GenAI Real — https://devreal.ai/e/240912-bay-area-... Explore these connections and related videos, photos, speakers’ blogs and podcasts, and other By the Bay networks. ----- DSPy: Prompt Optimization for LM Programs Michael Ryan, Stanford It has never been easier to build amazing LLM powered applications. Unfortunately engineering reliable and trustworthy LLMs remains challenging. Instead, practitioners should build LM Programs comprised of several composable calls to LLMs which can be rigorously tested, audited, and optimized like other software systems. In this talk I will introduce the idea of LM Programs in DSPy: The library for Programming — not Prompting LMs. I will demonstrate how the LM Program abstraction allows the creation of automatic optimizers for LM Programs which can optimize both the prompts and weights in an LM Program. I will conclude with an introduction to MIPROv2: our latest and highest performing prompt optimization algorithm for LM Programs. Michael Ryan is a masters student at Stanford University working on optimization for Language Model Programs in DSPy and Personalizing Language Models. His work has been recognized with a Best Social Impact award at ACL 2024, and an honorable mention for outstanding paper at ACL 2023. Michael co-lead the creation of the MIPRO & MIPROv2 optimizers, DSPy’s most performant optimizers for Language Model Programs. His prior work has showcased unintended cultural and global biases expressed in popular LLMs. He is currently a research intern at Snowflake.