Cover Image for 🦄 ai that works: Entities: Deduping, Resolving, Extracting
Cover Image for 🦄 ai that works: Entities: Deduping, Resolving, Extracting
Avatar for Boundary
Presented by
Boundary
We make BAML, a programming language for using LLMs. Some event recordings are available here: https://github.com/hellovai/ai-that-works

🦄 ai that works: Entities: Deduping, Resolving, Extracting

Zoom
Registration
Past Event
Welcome! To join the event, please register below.
About Event

🦄 ai that works

A weekly conversation about how we can all get the most juice out of todays models with @hellovai & @dexhorthy

https://www.github.com/hellovai/ai-that-works

Entity resolution and deduplication has been a data science topic since long before even classical ML hit the scene. LLMs change everything and make incredible new things possible, but as always, there are still engineering techniques that you can use to push the boundaries of performance, accuracy, and efficiency.

This week, Dex and Vaibhav will dive deep into how to build mature, effective LLM pipelines for deduping and consolidating Company entities in a resume / biography processing pipeline.

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 (A vscode replacement)

  • 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 Horothy, founder at Human Layer - a YC company. He spent 10+ years building devops tools at Replicated, Sprout Social and JPL. DevOps junkie turned AI Engineer.

Avatar for Boundary
Presented by
Boundary
We make BAML, a programming language for using LLMs. Some event recordings are available here: https://github.com/hellovai/ai-that-works