No, AI agents did not discover a previously unknown Maya site

Google researcher Pietro Miotti, working on what he called a personal side project, set 48 AI agents to scan NASA lidar data and announced a possibly unmapped Maya village in Mexico. Mexico's National Institute of Anthropology and History told him it had no registered site at that location. But the site had already been documented in an academic journal more than a year earlier.

Archaeologists pushed back hard online. The episode shows a growing tension: AI tools let amateurs work in specialist fields quickly, but without the expertise to know what's already known.

We want to be fair to Miotti. He said up front he wasn't an archaeologist, asked the Mexican authorities before going public, said fieldwork would be needed to verify the finding, and updated his post to credit the earlier work once people pointed it out. University College London's Elizabeth Graham said he did a decent job mapping mounds from lidar. That's more care than a lot of AI discovery claims get.

The failure was the framing. Calling it proof of a revolution across every science, after 72 hours, skipped the hardest part of research, which is knowing the literature. As Miotti acknowledged, archaeologists don't publish site coordinates, so checking a find means comparing images with figures in papers. His agents couldn't do that. A database with no record isn't the same as an unknown site.

The experts' deeper point lands. Graham says the field's problem isn't finding sites. Many are known and simply unexplored for lack of funding. Local communities often already know they're there. Ivan Šprajc, a co-author of the paper documenting the site, said spotting something doesn't add much to knowledge and that he's already getting more emails from AI "discoverers." He also flagged a real harm: publicizing site locations can attract looters.

This is where it leads if it scales. AI makes generating claims cheap. Checking them stays expensive and falls on the experts. If thousands of hobbyists send agent findings to underfunded researchers, we get noise, burnout and occasional damage to the sites themselves.

Still, I don't think the lesson is to keep AI out. Miotti says archaeologists and PhD students have asked about his workflow for their own survey data. That's the useful version: agents helping experts sort huge datasets, with experts setting the questions and checking the answers. We'd love to see that partnership, not another viral claim.

Lidar uses lasers to build detailed 3D maps and can reveal structures under forest cover. Archaeologists have used lidar and other remote sensing for years. The Verge notes a similar pattern in mathematics, where AI-produced results sometimes duplicate earlier work or fail to credit it.