Not in the Register, Already in the Literature

Pietro Miotti, a researcher at Google, wrote a blog post this month titled My AI Agents (Re)discovered a Maya Site in 72 Hours. The “(Re)” was added later. In the first version, his agents had found a Classic Maya civic centre on a hilltop in Mexico: a levelled plaza, an oval pyramid “at least 8–12 m tall,” a raised courtyard and what might be a reservoir. Mexico’s National Institute of Anthropology and History (INAH) confirmed in writing that “no registered archaeological site was identified at the location given in your report.”

Then archaeologists noticed. The update at the top of the post, dated 11 November, says the site “had already been mapped in Estrada-Belli et al. 2025. The agents missed it while going through the literature.” The Verge ran the story on 12 November with Sarah Parcak of the University of Alabama at Birmingham saying “This is why we have peer review.”

It’s easy to pile on, and I don’t want to. Miotti says plainly that he isn’t an archaeologist and that the find would need fieldwork. He corrected the post quickly and credited the people who had mapped the site. What interests me is the step where the claim went wrong. The agents found the site without trouble. The failure came at the novelty check, and the evidence that seemed to settle it, a heritage register with no entry for that spot, could hardly have settled anything. Archaeologists have measured how little a register tells you.

Seventy-two hours, thirteen years of data

The diary is short. On 18 October, travelling in Peru, Miotti wondered what Hiram Bingham would have done with modern tools. That night he had agents turn public lidar strips, “about 1,200 km² of jungle,” into images, and “48 agents went through them one by one like very patient archaeologists, looking for pyramids, platforms, and plazas.” He stresses: “There was no special model or classifier involved: the agents literally looked at the pictures, following a precise guide.” On 19 October he asked them to check “which of these villages haven’t been discovered yet” in the literature and archives, and one came back unregistered. He sent INAH a report on 20 October and had a reply on 21 October.

The lidar itself has a longer history. Miotti’s post labels its lidar view “2013” and sends readers to Cook et al. 2013, the paper describing NASA Goddard’s G-LiHT airborne imager. That paper says G-LiHT had already “been used to collect more than 6,500 km2 of data for NASA-sponsored studies across a broad range of ecoregions in the USA and Mexico.” It was flown for ecosystem science, not archaeology. Archaeologists picked it up anyway. Golden et al. 2016 reported a first archaeological assessment of “extensive transects of lidar recently collected by environmental scientists over southern Mexico using the G-LiHT system.” Archaeologists have kept coming back to environmental lidar from this region ever since.

The lidar was public and studied for years before the agents saw it Timeline from 2013 to 2026. August 2013: Cook and colleagues describe NASA's G-LiHT imager, which had flown more than 6,500 square kilometres in the USA and Mexico. October 2016: Golden and colleagues publish an archaeological assessment of G-LiHT transects over southern Mexico. October 2024: Auld-Thomas and colleagues report previously unrecorded urbanism in environmental lidar from Campeche. October 2025: Estrada-Belli and colleagues publish settlement models for a 95,000 square kilometre area using reprocessed environmental lidar. 18 to 21 October 2026: Miotti's 48 agents scan about 1,200 square kilometres and INAH replies that no site is registered at the location; on 11 November Miotti updates the post to say the site was already mapped in Estrada-Belli 2025. PUBLIC LIDAR AND THE MAYA LOWLANDS · 2013–2026 · SOURCES IN REFERENCES 2013 2016 2020 2024 2026 August 2013 — Cook et al., Remote Sensing 5(8) October 2016 — Golden et al., JAS: Reports 9 October 2024 — Auld-Thomas et al., Antiquity 98 October 2025 — Estrada-Belli et al., JAS: Reports 66 18–21 October 2026 — Miotti's agents and INAH's reply; 11 November update Aug 2013 · NASA paper on G-LiHT 18–21 Oct 2026 · 48 agents, ~1,200 km² Oct 2016 · Archaeologists assess G-LiHT Oct 2024 · Campeche environmental lidar Oct 2025 · Estrada-Belli et al., 95,000 km² area 6,500+ km² flown in the USA and Mexico INAH: no registered site · 11 Nov: "already mapped" transects over southern Mexico unrecorded cities in non-archaeological data the paper Miotti says already mapped the site Dates are journal issue or publication dates. The 2026 marker covers the agent run and the INAH reply.
The agents took 72 hours. The data had been public since around 2013 and archaeologists had been publishing from it for a decade.

The two papers nearest the site make this concrete. Auld-Thomas et al. 2024, in Antiquity, analysed an environmental lidar dataset from Campeche, collected for non-archaeological purposes, and found urban centres and dense settlement nobody had recorded. They argue that both are common across the central Maya Lowlands. Estrada-Belli et al. 2025 combined public and privately commissioned lidar, including reprocessed environmental lidar from southern Campeche and southern Quintana Roo, to model settlement and estimate a Classic-period population of 9.5 to 16 million across a 95,000 km² area of the central lowlands. That’s the paper Miotti’s update names.

How big 1,200 km² is

1,200 km² is not a small search for one person on holiday. But the useful comparison is the area archaeologists had already worked through in the same data. To scale, it looks like this.

Areas examined, drawn to scale Areas in square kilometres. Magnoni and colleagues' central Yucatán lidar evaluation: about 48. Challis and colleagues' Dove valley lidar study in England: 107. Miotti's agent scan: about 1,200. G-LiHT data collected by 2013 across the USA and Mexico: more than 6,500. Estrada-Belli and colleagues' central Maya Lowlands study area: 95,000. On a linear scale the agents' area is a sliver next to the regional study. AREA EXAMINED · KM² · LINEAR SCALE Yucatán ground check (2016) Dove valley, England (2008) Miotti's 48 agents (2026) G-LiHT flown by 2013 Estrada-Belli et al. (2025) ~48 km² — Magnoni et al. 2016 107 km² — Challis et al. 2008 ~1,200 km² — Miotti, blog post, November 2026 More than 6,500 km², USA and Mexico — Cook et al. 2013 95,000 km² — Estrada-Belli et al. 2025 ~48 107 ~1,200 6,500+ (USA and Mexico) 95,000 The 48 and 107 km² bars are drawn at a 1 px minimum. The G-LiHT figure covers all study sites, not only the Maya region.
The agents' scan was about 1.3% of the area in the paper that had already mapped the site.

Run the agents over a small corner of a region that a 2025 paper has already covered, and most of the hits will be sites somebody has already drawn. Finding one that isn’t would have been the surprise. A careful search would have treated “already published” as the default.

Spotting a pyramid is the easy part

Lidar under forest is hard to read, and archaeologists have measured how hard. Magnoni et al. 2016 took about 48 km² of high-density lidar from central Yucatán and checked it against areas that had been mapped on foot. Three of the authors went through the imagery separately and counted residential platforms and isolated structures larger than 5 × 5 m. They left out pyramids and monumental buildings, which they describe as “clearly identifiable in the lidar imagery.”

Share of ground-mapped house structures visible in lidar, central Yucatán From Table 1 of Magnoni and colleagues, 2016: percentage of ground-mapped residential structures larger than 25 square metres that could be identified in lidar, with false positives. Yaxuná centre: 53 of 122, 41 percent, 5 false positives. Yaxuná Sacbé 1 transect: 13 of 46, 28 percent, 5. Joya: 10 of 44, 23 percent, 4. Tzacauil: 3 of 13, 23 percent, 6. X-auil: 2 of 10, 20 percent, 3. Popolá: 11 of 46, 24 percent, 6. Yaxuná–Popolá transect, north edge of Yaxuná: 7 of 28, 25 percent, 5. Yaxuná–Popolá rural hinterland: 2 of 6, 33 percent, 7. In total 101 of 315 structures, 32 percent, with 41 false positives. HOUSE STRUCTURES FOUND IN LIDAR VS ON FOOT · MAGNONI ET AL. 2016, TABLE 1 False positives Yaxuná centre (53/122) Yaxuná, Sacbé 1 (13/46) Joya (10/44) Tzacauil (3/13) X-auil (2/10) Popolá (11/46) Transect, Yaxuná edge (7/28) Transect, hinterland (2/6) 41% — Yaxuná centre, Magnoni et al. 2016 28% — Yaxuná Sacbé 1 transect 23% — Joya 23% — Tzacauil 20% — X-auil 24% — Popolá 25% — Yaxuná–Popolá transect, north edge of Yaxuná 33% — Yaxuná–Popolá transect, rural hinterland 41% 28% 23% 23% 20% 24% 25% 33% 5 5 4 6 3 6 5 7 Total: 101 of 315 ground-mapped structures (32%) identified, with 41 false positives. Monumental architecture excluded. Counts are averages of three co-authors' independent passes over the imagery.
Below the monuments, lidar misses most of what is on the ground. In the rural hinterland the readers marked more false structures (7) than there were real ones in the count (6).

Across the whole table, 101 of 315 structures that had been mapped on the ground could be identified in the lidar, which is 32%, and the readers marked 41 false positives. The authors give three causes: bedrock hummocks one to six metres high “which morphologically mimic house mounds,” dense understory that degrades the bare-earth model, and low foundations lost in “the textural noise of the near-ground vegetation.” They also found that each reader had a habit. Some under-identified and some over-identified, “indicating a personal bias.” Their conclusion is that lidar in that part of the Maya region “should be used as a complement to traditional on-the-ground survey techniques.”

Miotti’s agents had the easy case. A plaza with an 8 to 12 m pyramid on a hilltop is the kind of feature that paper leaves out because anyone can see it. The agents never had to tell a house mound from a bump in the bedrock. The run doesn’t show they could, and Miotti’s post doesn’t claim it does. So it tells us little about how well agents read lidar. It shows they can find monuments where monuments are obvious, which human readers could already do.

What a register leaves out

INAH’s letter was the strongest evidence in the original post, and it was accurate. INAH didn’t have the site in its register. The mistake was treating that as meaning nobody had recorded the site.

Challis et al. 2008 measured this gap in England. They took 107 km² of Environment Agency lidar over the Dove valley, mapped 915 archaeological features and compared them with the county Historic Environment Records, the UK equivalent of a site register.

Lidar-derived features already in the county records, Dove valley From Table 2 of Challis and colleagues, 2008. Of 915 archaeological features identified in lidar of the Dove valley, 772 (84.4 percent) were not in either county's Historic Environment Record, 79 (8.6 percent) were already in the Staffordshire record and 64 (7.0 percent) in the Derbyshire record. 915 LIDAR FEATURES VS THE HERITAGE REGISTER · CHALLIS ET AL. 2008, TABLE 2 Not in either county record Already in Staffordshire record Already in Derbyshire record 772 features, 84.4% — Challis et al. 2008, Table 2 79 features, 8.6% — Challis et al. 2008, Table 2 64 features, 7.0% — Challis et al. 2008, Table 2 772 · 84.4% 79 · 8.6% 64 · 7.0% Most features were agricultural, mainly ridge and furrow. The point is the register's coverage, not the novelty of each feature.
In a well-studied English valley, 84.4% of what lidar showed was missing from the official record. Being absent from a register is the normal case for a lidar feature.

772 of the 915 features, 84.4%, were “not previously noted in the Historic Environment Record.” Most were agricultural remains, mainly medieval ridge and furrow, which is hardly news to anyone, so this doesn’t mean lidar finds 772 new sites. It means registers are built from what got reported through official channels, and a lot of what specialists know never reaches them. The same study also found the reverse: records the lidar couldn’t see, such as cropmarks, finds, documentary entries and standing buildings.

The Maya lowlands should make this gap bigger. Estrada-Belli and colleagues model settlement across 95,000 km². I doubt any national register logs every plaza group a regional settlement model picks up. Miotti put it himself in his comments to The Verge: “Archaeologists rightly don’t publish the coordinates of sites, so checking whether a site is already known means comparing images against figures in papers, not searching a database.” That’s the right diagnosis. With coordinates withheld and registers incomplete, the novelty check has to be done against maps and figures in papers, and that’s where the agents failed.

What I’d take from it

I’d read the 72 hours the other way from how the post presents it. Detecting an obvious monument in public lidar was fast because it was easy. Recognising an already published site in a paper’s figures, when the paper won’t print coordinates, is slow because it’s hard. And the public claim of a find rested on a register lookup that the literature has long known to be weak evidence.

If I were building agents for this kind of work, three things would change.

Miotti ends the post by saying “we should probably lidar the whole planet and let the agents discover the rest.” More lidar would be good. But in the region he tested, the slow step came after the data. It was finding out what archaeologists had already published, and not reading a register’s silence as a discovery.

References

  1. Miotti, P. (2026). My AI Agents (Re)discovered a Maya Site in 72 Hours. Blog post, last edited 11 November 2026.
  2. Hart, R. (2026). No, AI agents did not discover a previously unknown Maya site. The Verge, 12 November 2026.
  3. Estrada-Belli, F., Canuto, M. A., Šprajc, I. and Fernandez-Diaz, J. C. (2025). New regional-scale Classic Maya population density estimates and settlement distribution models through airborne lidar. Journal of Archaeological Science: Reports 66, 105288, October 2025.
  4. Auld-Thomas, L., Canuto, M. A., Velázquez Morlet, A., Estrada-Belli, F., Chatelain, D., Matadamas, D., Pigott, M. and Fernández Díaz, J. C. (2024). Running out of empty space: environmental lidar and the crowded ancient landscape of Campeche, Mexico. Antiquity 98(401), 1340-1358, October 2024.
  5. Golden, C., Murtha, T., Cook, B., Shaffer, D. S., Schroder, W., Hermitt, E. J., Alcover Firpi, O. and Scherer, A. K. (2016). Reanalyzing environmental lidar data for archaeology: Mesoamerican applications and implications. Journal of Archaeological Science: Reports 9, 293-308, October 2016.
  6. Cook, B., Corp, L., Nelson, R., Middleton, E., Morton, D., McCorkel, J., Masek, J., Ranson, K., Ly, V. and Montesano, P. (2013). NASA Goddard’s LiDAR, Hyperspectral and Thermal (G-LiHT) Airborne Imager. Remote Sensing 5(8), 4045-4066, 13 August 2013.
  7. Challis, K., Kokalj, Z., Kincey, M., Moscrop, D. and Howard, A. J. (2008). Airborne lidar and historic environment records. Antiquity 82(318), 1055-1064, December 2008.
  8. Magnoni, A., Stanton, T. W., Barth, N., Fernandez-Diaz, J. C., Osorio León, J. F., Pérez Ruíz, F. and Wheeler, J. A. (2016). Detection Thresholds of Archaeological Features in Airborne Lidar Data from Central Yucatán. Advances in Archaeological Practice 4(3), 232-248, August 2016.