Hybrid MI Python: Michigan Python

Presenter: Eric Humphrey

Title: Python -> English -> Code: Viewing LLMs as Information Compression

Description: This talk proposes a new way to think about LLMs: as a compression-decompression pipeline. We "compress" complex Python logic into a compact natural language representation, and then use an LLM to "decompress" that information back into functional code. We explore how inherently "lossy" this compression is, look at what is "lost" in translation (syntax, variable names), and what is preserved (hopefully function, logic). Understanding this analogy can help us become more effective at using LLMs to write maintainable code.

AGENDA:
7:00pm - Opening announcements
7:10pm - Main Topic
7:50pm - Q&A