AI Tinkerers Seattle July 2024

AI Tinkerers July 2024

Joe Golden (PerfectRec): an AI-powered laptop recommendation system combining LLMs with curated data

Boris Smus (Google): Use GPT4’s multimodal features to accelerate and improve my recently rebooted Visual Chronology of Science & Discovery project now hosted at https://invention.cards 

Marnel Ramirez: Presented an AI Patient Case Study Generator for healthcare education.

Patient Case Generator

Rajesh Korde (Smartsheet): Introduced ExamGPT, an AI tool for generating study flash cards.

ExamGPT

Kelly Han (Johnson & Johnson): Showcased a multi-agent orchestration framework for clinical trial data analysis.

Vaibhav Gupta (Boundary): Discussed BAML, an algorithm for reliable JSON parsing from LLM responses. Baml programming language makes it easy to deal with RAG and formatted data. Uses edit distance to efficiently reformat to output. https://github.com/boundaryml/baml

BAML Presentation

Ash Srinivas (Johnson & Johnson): Demonstrated SupaLlama v0.2 for building dockerized LLM apps without vendor lock-in.

Goncalo Martins Ribeiro (YData): Explored synthetic data generation using open-source Python libraries.