Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Moneyball: Data Decisions and Bias
This talk explores how human biases affect data-driven decisions, using a baseball example to highlight the value of simplicity in statistical models.
We tend to believe that data-driven decision-making is the epitome of objectiveness, but as humans we are subject to several types of biases which tend to accommodate the narrative. And these biases tend to be replicated in the data we store and the models we create with it. We’ll illustrate this with a baseball example taken from Michael Lewis’ classic “Moneyball”.
Related projects
Tables and AI
Seattle
Learn how to use spreadsheet tables to define, prioritize, and evaluate LLM rules and prompts, enabling stakeholders to…
Demo: Dendron - AI-Powered Analysis for Technology/AI Adoption
Miami
Live demo shows multi‑agent LLMs mapping business processes and technology landscapes, maintaining context across analysis and quantifying confidence…
IDEAR
Bogotá
The talk explains a web app delivering interactive 3D product models, its analytics pipeline, infrastructure choices, and compares…
Model and Prompt Evals the Hard Way
New York City
Learn to evaluate models and prompts using simple Jupyter notebooks, applying manual reviews and automated metrics to compare…
Building Magic the gathering decks using AI
Medellín
This talk explores building Magic: The Gathering decks using basic AI techniques like tf/idf to calculate card synergy…
The Unreasonable Power of Structured Outputs
Paris
This talk demonstrates three applications using structured outputs: a PowerPoint generator, a smart search bar, and a skin…