
Share
Archaeologists and AI enthusiasts are invited to join OpenAI’s "OpenAI to Z Challenge," where cutting-edge technology meets ancient mysteries in the dense jungles of the Amazon.
May 15, 2025
OpenAI has announced the launch of the "OpenAI to Z Challenge," a unique competition aimed at identifying potentially hidden archaeological sites within the Amazon biome. This challenge leverages OpenAI's latest models-o3/o4 mini and GPT-4.1-to analyze open-source data, including high-resolution satellite imagery and LIDAR scans.
The Amazon Rainforest spans over 6 million square kilometers across nine countries, making it a vast and largely unexplored region rich in historical significance. The challenge focuses on Brazil but extends to the outskirts of Bolivia, Colombia, Ecuador, Guyana, Peru, Suriname, Venezuela, and French Guiana. The goal is to use AI to uncover new archaeological sites that are often hidden beneath dense forest canopies.
Data Sources: Participants will work with a variety of data types:
AI Models:
Participants are tasked with the following:
Identify Potential Sites:
Gather Historical Insights:

The challenge is structured into several key phases:
Submissions are due by June 29, 2025. The evaluation criteria include:
The top five teams will be shortlisted, and their discoveries will be live-streamed with a panel of subject matter experts from OpenAI and other institutions. A mystery AI leader will also join the panel to select the winning team.
This challenge is not just about discovering new archaeological sites; it's about fostering collaboration between technologists, archaeologists, and Indigenous communities. By leveraging advanced AI models and open-source data, participants can contribute to preserving historical sites that are under threat from deforestation and development.
Join the "OpenAI to Z Challenge" today and be part of a groundbreaking initiative that combines cutting-edge technology with historical exploration.
Tags
Original Sources
About the author
Kai built ML infrastructure at a Bay Area startup before developing an obsession with transformer architectures and inference optimisation that eventually pulled him out of product work entirely. A stint at a compute research lab sharpened his instinct for what actually matters in a model release versus what is marketing. He writes from the inside — from the perspective of someone who has debugged the systems he is describing at three in the morning. He is allergic to hype and instinctively drawn to the unglamorous plumbing questions that everyone else skips over.
More from The Engineer →This Week's Edition
19 May 2025
133 articles
Related Articles

Smarter Engagement for Stronger Growth: How Payers Can Leverage AI to Do More with Less
Products & Applications · 3 min

Penn Medicine and K Health Deploy AI Clinical Agents to Enhance Patient Care
Products & Applications · 3 min

Wheel and b.well Partner to Build Turnkey AI-First Virtual Care Infrastructure
Products & Applications · 3 min
Related Articles

Smarter Engagement for Stronger Growth: How Payers Can Leverage AI to Do More with Less
Products & Applications · 3 min

Penn Medicine and K Health Deploy AI Clinical Agents to Enhance Patient Care
Products & Applications · 3 min

Wheel and b.well Partner to Build Turnkey AI-First Virtual Care Infrastructure
Products & Applications · 3 min
More Stories