Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Claude Haiku Trading Card Pipeline
This talk demonstrates an automated pipeline that converts financial data into dynamic trading cards using LLMs, image generation, and meta-prompting techniques.
A demo of an automated pipeline that transforms financial market data into a dynamic trading card game. I’ll show the complete system: from data extraction to LLM-powered creature generation to final card artwork creation. Includes live generation examples and useful techniques like meta-prompting, where one AI model optimizes prompts for another.
Related projects
Enhancing Application Data and Logic with OpenAI Functions
Chicago
This talk demonstrates how OpenAI Functions can convert AI-generated text into JSON to enhance data handling and application…
AI powered component streaming with structured outputs
New York City
This talk demonstrates how to obtain more reliable outputs from LLMs and use structured data to stream dynamic…
Building Municipal AI: Natural Language Interfaces for Public Data and Legal Code
Chicago
A live demo of Municodex, showing how natural‑language queries retrieve and summarize Chicago data portal records and municipal…
Better Insights into Team Activity
Los Angeles
The session demonstrates a Jupyter Notebook proof‑of‑concept that combines usage‑tracking dashboards, forecasting models, and a retrieval‑augmented LLM to…
AI Startup Scout
Seattle
A sub‑agent scans Hacker News, flags potential startup stories, adds founder data from external sources, and generates concise…
Synthetic Data
Chicago
This talk explores practical methods for generating synthetic data to improve model performance when real data is limited…