Software engineer's AI agents flag unmapped Maya structure from NASA lidar data
A Google software engineer describes setting roughly four dozen AI agents (from Gemini, ChatGPT, Claude and Grok) to analyze publicly available NASA lidar scans of the Maya region in Mexico. Within about 72 hours, the process surfaced what appears to be a previously unreported archaeological site, and Mexican authorities acknowledged the finding, according to the engineer's account.
GoKawiil's interpretation of the reporting above, not reported fact.
The episode suggests AI tools could speed up archaeological survey work by scanning vast troves of remote-sensing data that researchers would otherwise sift through manually, potentially surfacing leads human teams had missed. However, the account comes from a non-archaeologist hobbyist project rather than a peer-reviewed survey, so the significance of the specific site and the reliability of AI-driven detection at scale remain to be independently verified by experts.
- An engineer used about 48 AI agents to analyze NASA lidar data covering the Maya region.
- The process reportedly identified an unreported site within roughly 72 hours, with Mexican officials responding to the claim.
- The account highlights lidar's ability to reveal ground features hidden under jungle canopy that satellite imagery cannot show.
Source: pietromiotti.com, 2026-11-11
Published there as: “Google SWE points 48 AI agents at NASA Lidar, finds unmapped Maya pyramid in 72h”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.