a weekly conversation about how we can all get the most juice out of todays models with @hellovai & @dexhorthy
📅 event calendar - https://lu.ma/baml
every tuesday at 10 am pst on zoom.
1 hour of live code, q&a with some prepped content to help you take your ai app from a demo to production.
lets code together 🧑💻
to prevent repeating the basics, we recommend you come in 5CA0 having already understanding some of the tooling we will be using:
- zoom
- cursor (a vscode alternative)
- programming languages
- application logic: python or typescript or go (depends on session)
- prompting: baml
- repo: github.com/boundaryml/baml
- recommend getting started video
- package managers of choice:
- Python - UV
- Typescript - PNPM
| topic | description |
|---|---|
| 2025-03-31 large scale classification youtube • code • RSVP |
llms are great at classification from 5, 10, maybe even 50 categories. but how do we deal with situations when we have over 1000? perhaps its an ever changing list of categories? |
| 2025-04-08 reasoning models vs reasoning prompts youtube • code • RSVP |
models can reason but you can also reason within a prompt. which technique wins out when and why? we'll find out by adding reasoning to a chat bot that generates complex cypher/sql queries. |
| 2025-04-15 code generation with small models Youtube • code • RSVP |
large models can do a lot, but so can small models. we'll discuss techniques for how to leverge extremely small models for generating diffs and making changes in complete codebases. |
| 2025-04-22 twelve factor agents Youtube • code • RSVP |
learn how to build production-ready AI agents using the twelve-factor methodology. we'll cover the core concepts and build a real agent from scratch. |
| Break | We had a great time doing the first four episodes of AI that Works - we'll see y'all may 13th for season 2! |
| 2025-05-13 you're doing evals wrong youtube • code • RSVP |
stay tuned for our season 2 kickoff topic on minimalist and high-performance testing/evals for LLM applications |