Google researcher's AI agents locate a Maya site already published in a journal

On October 18, 2026, Pietro Miotti, a Google researcher who describes himself as not being an archaeologist, was traveling in Peru and reading about Hiram Bingham, the explorer who reached Machu Picchu in 1911. Wondering what Bingham would have done with today's tools, he pointed a group of AI agents at public NASA lidar data that night. By October 21, he had received an official reply from the Mexican government about a Maya site hidden beneath the jungle. On November 11, he added an update at the top of his post noting that archaeologists had already mapped the site, and reflected on what the agents managed to do and where they failed.

On November 12, DEV Community covered the effort, reporting that 48 AI agents scanned roughly 1,200 square kilometers of NASA lidar data across the Maya region in a single night. They flagged a hilltop site containing a plaza, an oval pyramid at least 8 to 12 meters tall, a raised courtyard, and a possible reservoir, and Miotti said the whole process took 72 hours. The report also stated that Mexico's national archaeology institute had no record of the site.

On November 13, The Verge reported a conflicting account, noting that Miotti had claimed earlier that week to have discovered a potentially unmapped Maya site in Mexico, yet the site had already been discovered and published in an academic journal the previous year. The incident drew criticism from archaeologists online, and The Verge argued it shows that conclusions reached by AI agents still require human verification. The matter currently stands at this point, with the two accounts differing over whether the location was a genuinely unknown find.