Now I'm very interested in seeing the transcript/session from what the agent actually did.
We already know since before that agents takes all sorts of possible shortcuts to find the answer they think the user was looking for. It doesn't seem impossible to me that the user asked something that made the agent feel OK with highlighting something that wasn't logged in the Mexican database as a novel discovery, even if it wasn't.
But again, transcripts/session logs would make it extremely clear exactly what has happened, and I'd take the author not publishing those as trying to hide something about how the agent actually approached this.
> This story is going wild on X and elsewhere. The site was already published by Dr. Francisco Estrada-Belli of Tulane University ages ago. This is why we have peer review. Mexican gov didn't have it in their database, but that doesn't mean it is unknown/unmapped.
https://pietromiotti.com/latest/maya-site/
Basically: already known, not in the Mexican Gov database, but in published literature.
This story is very cool, and it’s exciting to see how much progress AI will bring to every field. One thing to temper everyone from wanting to lidar the whole world is human capacity. Finding discoveries like this is essentially as hard as doing the lidar mapping. Now the issue will be getting archaeologist there in time before someone else does.
The best way to protect a site is to leave it alone. If we start finding dozens or hundreds of sites it will be more than what archaeologists can excavate and protest. Treasure hunters and looters don’t care about stratigraphy and the processes involved for doing research. Maybe the cat is out of the bag on this one, but good for thought.
Edit: I’m not saying we shouldn’t have people use AI to do this or that no bad actor will. This comment is in response to the sentiment I am seeing in the comments that we should lidar the whole world and have AI find any anomalous structures it can. There is no way for archeologists to excavate and protect all those places in that scenario
Given that treasure hunters and looters can also use the process outlined in this blog post, leaving it alone seems like a guarantee that it will be explored by looters first.
Why not? It isn't exactly a secret technology nor are LIDAR-equipped RC aircrafts/drones particularly out of reach in terms of cost either. What would stop them exactly?
Archeologists have been using Lidar equipped RC aircraft for quite some time now. With the way things are going it won't be too difficult to have a small swarm of UAVs doing the mapping soon.
It isn’t about having value or not. Some people in the comments are talking about using lidar on the whole world and seeing what agents find. Thats a great way to give looters all over the world the heads up so they can rush over and steal whatever they can. Any archeological site has valuable information on what a slice of humanity’s world used to be. Giving looters a head start means destroying that information often permanently.
A helpful example might be Heinrich Schliemann, a businessman who fancied himself an archaeologist and destroyed much of Troy’s history by digging it up as fast as he could. He was so focused on finding treasure to prove to world he was a great archaeologist he irreparably damaged the real layers that were Troy.
> His excavations were condemned by later archaeologists as having destroyed the main layers of the real Troy. Kenneth W. Harl, in the Teaching Company's Great Ancient Civilizations of Asia Minor lecture series, sarcastically claimed that Schliemann's excavations were carried out with such rough methods that he did to Troy what the Greeks could not do in their times, destroying and levelling down the entire city walls to the ground.
Well to be fair archeology as a profession did not really exist at that point, it was mostly rich peoples hobbies, or authoritarian rulers way of legitimizing their rule through an ancestry argument
This actually isn't entirely true and archeologists at his own time said they way he worked was bad and the Ottoman government tried to stop him. At one point he had to flee the site and could only get back by hiring a professional archeologist to help him.
> The best way to protect a site is to leave it alone. If we start finding dozens or hundreds of sites it will be more than what archaeologists can excavate and protest.
Ain't the site itself the most important thing? As opposed to items: looters won't steal the site?
Looters will absolutely destroy a site to find valuables that may or may not even be there. Ai-khanoum is a classic example, with the vast majority of the site having been filled with pits on the off chance there were valuables. Nowadays they use bulldozers and excavators to loot at an industrial scale. It's pretty difficult to do archaeology on a pile of sifted dirt.
Amazing, the perfect application of AI Agents. Find patterns/answers in massive amounts of data. It is becoming more clear everyday that this is the primary driver behind an AI's "intelligence". Finding the solution to mathematical problems that have decades of documented attempts by mathematicians, creating software based on exisitng code and now, discovering Maya pyramids within enourmous amounts of lidar-data.
The final barrier for super intelligence, or perhaps even just "human intelligence": can it materialize "new fields/ideas" without large datasets of human made and curated existing attempts?
I am curious how this things perform compared to a "classical" neural networks. Tasks like image classification, feature extraction has been studied extensively and there were a lot of very cool applications before (medicine included). The biggest obstacle was always data but even that could have been partly automated with some semi-supervised learning schemes.
Of course the Bitter Lesson applies here, given a big enough model, it can outperform specialised ones, but at this point it's not clear
1) By how much?
2) If this is even true in the first place or if we have the means to train much leaner networks
It is becoming a boring homogenous world where we are trading deep expertise with being able to query the magic box
I would assume, without actually having checked, that traditional neural networks have already been extensively run on this datasets. Seems like the "standard" thing to do anyways.
My guess is that you can find 99% of Maya pyramids in a Lidar set in a fairly short time with a traditional neural network, but you might find the last few using a network of AI agents, because they are capable of "creative" problem solving and using different methods/parameters/tools over several iterations.
There is no "final barrier", the goalpost will continue to change until you are not aware of what is going on anymore. This is already becoming true as the recently produced math research is not fully understood, CoT moves further away from looking like human reasoning and datasets become generated rather than collected from existing human data.
? CoT did not look like actual human reasoning from day one. It's just a context expansion mechanism, the purpose isn't actually to mimic human style reasoning, nor was it ever doing so. In the recent openAI article where they showed excerpts from the CoT, it looks like reasoning has moved even further from what i would call a human like flow of thought
Certainly, but at that point it becomes a philosophical question, rather than an empirical one.
Can we even measure an intelligence greater than our own? And at that point -- what is the point exactly? Why make an intelligence that we don't even know is intelligent? If its output is indiscernible to the human mind, what good does it do us?
The only "barrier" I can see that is valuable and that might be measureable to humans is this underlying mechanic of being able to create new ideas/concepts from little to no existing human generated training data. Otherwise, and as I see it right now, these machines will not become sentient, or go rouge, or be able to cure all future disease or solve all of physics, becasue they are entirely reliant on human made trainingsets.
Historically, for humans, this can not be the case, otherwise we would see no progress. Someone has to have a thought for the first time. Perhaps the solution to this for AI agents is some inherent randomness, and massive amounts of brute force compute. Who knows?
The point is the next epoch of evolution. Like humans made monkeys obsolete, LLMs will make humans and biological hardware obsolete. Maybe we will live in zoos, or maybe we will simply go extinct. Evolution places no special value on a particular species or hardware platform.
I think you have eaten too much of the LLM generated cake if you genuinely believe that LLM's are anywhere close to making humans and biological "hardware" obsolete. Sometimes we must ground ourselves and remember that we live in the real world and not Star Wars.
We can always just unplug the computer, you know. AI agents can do damage, they can be used in malicious ways and bring down/distrupt infrastructure, but the leap from today to the point where LLM's can prevent us from pulling the cord is unimagineable large, and likely infinite.
In modernity, the gap between the digital and material world is closing, especially from a sociological perspective, but we are still neurological systems spinning on a large rock. For 99% of our history we didn't have electricity. The likelyhood of returning to a post-electricty world, for example, is much greater than LLM's taking over the world and making us into zoo animals.
Now I'm curious if anyone has or might try to create an LLM that lacks all knowledge of the post-einstein/newton/plato world and see if it can figure things out. I imagine lack of training data would be a problem, but maybe it could be a way to reverse-engineer an effective prompt that can give us insight in the platos of our world?
They would need to be much better at learning. You can teach a child how to drive a car and they can be good enough at it that the state will grant them a license to drive.
Where's the learning robot that I can teach to drive a car in the same way? They can solve some complex math problem but can they read the cues of other drivers at a four way stop to know when they should go (knowing the rules isn't sufficient).
> I imagine lack of training data would be a problem
I imagine that's an understatement. Using only the written works available from before Einstein (let alone Newton or Plato), you'd probably need a whole new technology that could train itself without any training data other than observation of the world.
arguably it is feasible in principle to filter out that knowledge from later writings, but you can always say it leaked in a subtle way - "this chonky cat is bending space around it" (this is exaggerated, can be much more subtle and hard to notice)
Interesting. I don't want to sound like a hater or anything, but I will personally wait for an expert archaeologist's verification on this. I have dealt with agents making up stuff that sounds fantastic and ground-breaking but completely falters on further review. And I doubt the folks you contacted have the audacity to question a Google engineer and his 48 agents. Even if he is not archaelogist. Do you think it would have gone the same way if it was another random person who had done the exact same thing and reached out to them? The one day feedback part also has me questioning what they actually did.
Anyway, I can hear myself beginning to sound like a hater now, so I will stop here. I hope it turns out to be right, and in that case, congrats on your wonderful discovery.
Yeah I agree. There’s a lot of assumptions coming out about what the structures are and what it looks like that give me pause. Very cool to have found this site though. The actual archeology involved though will be slow as it’s a science done layer by layer. It will be interesting to see if any predictions made by the AI match up to the facts.
I’m the same for a couple of reasons. First I want to say it is refreshing that AI is being used for discovery instead of an AI arms race, or something else that just feels dystopian. I understand this is happening but it’s rarely what is shown.
1. They said there is no site there, does that mean no one knew it was there?
If this is official lidar data, I find it hard to believe that this is a true discovery, I assume that it just can’t be claimed as a discovery until someone goes there which can be expensive and requires government oversight.
No universities have created an application to detect irregularities in this dataset, that was possible with ML years ago.
2. Personally I want people to Start sharing how much it cost the agent to do a task, because it feels like cost is becoming the bottleneck. Yes it’s awesome it did X but does that mean this can be utilized by people, businesses, or just governments and big tech.
Also just because we’re skeptical doesn’t make us haters. Being a hater is speaking in bad faith.
I'm sceptical too. Perhaps he verified, but from his blogpost, he doesn't imply that he cross checked anything and instead trusted all agentic output. For example, after getting the patch of ladar with the site, did he manually check NASA's resources to make sure there was no hallucination there? Maybe his agents are really good, but submitting this to INAH after only chatting with the agents is really bold.
Again, maybe he did cross verify things and just left that out of the storytelling, and congrats because this is really cool.
“INAH replied: they checked their records and found no registered archaeological site at that location. To be clear, it's not official yet. But as far as anyone can tell, nobody had put this one on a map before.“
INAH said there's nothing registered there, nothing more than that. The results look fairly convincing but neither the OP, me and (I presume) you nor the commentor have archaeology experience. Perhaps there are other explanations for ground structures like this we just don't know till an expert visits the site and confirms that yes, it is a previously unmapped Mayan pyramid.
I'm certainly not one to defend AI bros, this guy's writing is insufferable (and reads like slop to me), but did you read TFA? The LIDAR image (based on measured data, not AI) clearly shows human-made structures, and the Mexican government's response said that it's not registered. The chatbots just found it. Unless he's completely lying about the whole thing, this seems genuine. Now all the bits about what sort of site it probably was and the slopified image of what it might have looked like are garbage, but the find itself doesn't look to be.
TBH the Academic reaction to this could likely be to gatekeep it into oblivion over bad faith or ideological reasons given the perceived hostile takeover of their domain by 'amateurs'.
We saw this with the Dead Sea Scrolls where exclusive control was given to a select group of academics who monopolized the research to the point of refusing to release photographs or transcripts for nearly 40 years. The Huntington Library eventually had to force their hand by releasing their microfiche copies.
Again, we saw this with both the Ochtendung Skull Fraud and the Piltdown Man fraud - systematically falsifying results for clout is an exclusively human pre-occupation.
More to the point, in May 2025 YouTuber MrBeast was allowed to film inside the off-limits areas of Mayan Temples; something banned for both locals and normal tourists.
Academics posit that strict peer review is necessary so as not to allow the hoarding and gatekeeping of knowledge. However in matters of verification, faslification, and justification, they are derelict in their duty to the other half of that contract. The field only has itself to blame if other fields start organically superseding their usefulness and eroding their domain exclusivity by proxy of poor governance and ways of working.
I mean we should all have axes to grind regarding bad actors demeaning academia and stilting academic progress because of ideological issues or financial incentives, should we not?
Pointing out the benefit of removing human malfeasance from a given system, and extrapolating likely outcomes if we don't based on cited recent malpractice, is hardly a polemic against the system. Merely an explanation of anti-scientific stances from a supposed scientific community whose own rules and processes have resulted in issues that likely would not arise from employing responsible agentic prompting as a research tool.
If I can point to exclusively human behaviour in the domain being the largest problem regarding credibility and progress of the field as a whole, I am obviously going to argue against giving that same compromised governance exclusive franchise over discoveries made in spite of its existence.
I think we are about to see a whole new age of "citizen scientists", enabled by AI. This particular example was solved fast with a lot of compute, but it seems that this approach would have been possible with less equipment too.
The bottleneck will be data. Every possible signal out of publicly available datasets will be squeezed fast.
I appreciate the enthusiasm. I'm not sure I agree. Especially since this was a SWE and not an archeologist / anthropologist announcing this (especially if the goal is to understand and preserve history -- not get headlines for AI).
Life is surrounded by nuances. The COVID pandemic was the best time to be alive if you were a tech worker and your family was safe and healthy. Now COVID is over, so does most of the value of our intellectual work.
If you're a Google SWE with 7 figure comp, doing experiments with agent swarms you don't need to pay for, with healthy case of Dunning-Kruger... then maybe it is.
It can, but then it runs into the Google Maps issue - everything altruistic at the expense of some bad actor becomes a Security, Military or Legal concern - and the apathy issue.
This is partly why George Clooney abandoned his Project Sentinel - documenting atrocities from space means nothing if you cannot action on the people and financial networks enabling them.
> This is partly why George Clooney abandoned his Project Sentinel - documenting atrocities from space means nothing if you cannot action on the people and financial networks enabling them.
At the very least you can try to hold the bad actors accountable even if it's years if not decades afterwards, if you have documentation. Germany for example had deathcamp criminal cases being prosecuted as late as 2022 [1].
It will get really interesting what happens in the US once the Trump administration is gone - even if the expected Trump pardon against everyone involved gets reversed somehow, I suspect that a lot of material regarding ICE or the military strikes against "drug smugglers" will simply have been shredded or never been created in the first place...
Seriously though, why 48 AI Agents? I'm curious, presumably one agent could parallelize its analysis so its not raw parallelism? Do the agents share work? This kind of agent scale is outside of my budget, I would love to know the details.
Well they had to look at lidar images from huge parts of Mexico. Seeing as 48 agents did it in 72 hours, presumably 1 agent would do it in 144 days.
Simple to enough to ask "how long would it take", see 144 days and reply "do it in 3 days" and the agent will happily spin up enough instances to cover it
edit: "presumably one agent could parallelize its analysis"
No, they said they didn't analyse with tool use it was literally agents "looking" at the images via multimodal input
Also agents analyzing drought pictures, where many ancient UK structures seem to appear would be an easy win. I've never checked whether there's a comprehensive drought picture map of the UK.
The UK landmass is really quite small compared to central America. I'd be surprised if there are many substantial structures left - geophys has been around a long time.
That is amazing! Great discovery and write up and motivation. Earlier in the week I got an FB impression of a LIDAR for Fort Stamford (CT), superimposed with the satelite footage and pondered what other hidden constructs might be lurking around here. And all you got to set up the loop asking for it...
People have been finding hidden constructions for a while. The large urban conurbations such as around Ecuador are perhaps the most impressive (https://apnews.com/article/amazon-lost-cities-ecuador-archae...). While Archeologists have been driving the process almost anyone who spends time with recent LIDAR data finds something much as how publicly available satellite data has uncovered geological oddities. This is not a big advance. Getting an official report completed and creating a compelling image of what the site might have looked like is impressive, but also consistent with what ordinary untrained people have been accomplishing.
I think it matters because "I used 48 agents running for 72 hours" either means you invested $50,000 of your own money, or you work for a company that gives you unlimited tokens.
"Will the AI work better because it was "pointed" by a Google SWE?"
Usually yes? (vs pointed by a random vibe coder)
Also the more interesting bit to me here is, that you do not find the reference on the page at all, that the person works for google at all (I only found it mentioned in his X account). With the headline I initially thought this was a official google research project, but the blog reads like a personal project.
I know what you're saying. At the same time, this is someone using the technical skills in wielding a technology to make, unverified sure, discovery in a wholly different field, but in which they are presumably interested.
So for me one key takeaway is how AI could possibly open up more interdisciplinary work in our heavily siloed world.
How do we know that this is a good thing? Putting a "Ruin here!" pushpin on a map and leaving the actual archeology to others sounds more like a vanity boost than an achievement, and at worst the opportunity for the site to be desecrated before anyone serious has a chance to study it.
It's like the new drive-by pull requests I'm getting in my open source repositories. No consideration for the people doing the actual work.
Which is why he specifically didnt give a pushpin, and censored out the location and the region in the mail? Also whats stopping the bad actors from doing this work themselves (aside from the price, which im sure could be optimized for, if you don't have an unlimited budget of tokens), and then looting them while the real scientists are none the wiser?
You've heard about humans doing pattern recognition based on established baselines? Hold my beer when I blow your mind about recent developments in computing.
To writ, parsing massive LiDAR datasets to spot repetitive, distinct geometric patterns is something that AI excels at. They are not subject to facial pareidolia like humans are - they have no hard-wired weighting to impose meaningful patterns onto random or ambiguous visual stimuli.
But they do what you tell them, so be convincing enough and the patterns will emerge, I think even with something silly like "be creative, imaginative and ignore science, in the following images find any resemblance of a face, no matter how far fetched" will give all kinds of silliness.
I mean try it, but their internal prompts usually restrict them from spouting disinformation on purpose, so even if you got a response like that, it would finish with something like this is of course all in the context of our roleplaying situation and has no bearing on irl results. Also the sycophancy in general has been improved greatly, they don't agree with you on everything anymore
To paraphrase Hitchens, anything tenuously asserted by agentic AI can be easily repudiated by agentic AI. The knife cuts both ways, and agentic output tends towards Occam's Razor as its defined edge.
Now will we have a TempleOS style burning bush that goes beyond the markov-chain limitations of Terry Davis' era? Very likely. Will it impact contemporary discourse? About as much as the Astrology and Homeopathic mobile apps.
(N.B. I am conscious that Homeopathy is a $14bn market segment in the US. Notwithstanding, given that the segment is based on magic-water-'science', I think the point remains.)
It would not have been realistic to have PhD students manually comb through thousands of square kilometers of LIDAR data, and crossreference everything with existing sites; LLMs have turned this into low-hanging fruit.
Can't expect every single scientific field to immediately use any new technology to its full potential, and it makes you sound like a prick, too.
Excusing a scientific field not embracing paradigm-shifting new developments isn't even an argument.
The real answer is financial incentives tied to publishing of research - something that academics in gatekept fields see as the thin edge of the wedge in exposing a utility/ROI gap for legacy practitioners.
The world has general access to AI since years. Imagine you spend your life as archeologist, then when a new technology comes along that could revolutionize your field, you ignore it. Using AI to classify/search for locations is such a no brainer, that asking why it is not the norm, is a valid question. Humans should review the findings, but the boring work should probably be done by the machines.
I have to be frankly honest -- I have a gut feeling -- regardless of what Pietro reported to the Mexican gov't, the binary response professionally is likely "Sorry, we didn't find it".
There is no reason for them to provide confirmation for internal inventory that Pietro passionately fingered from afar.
Which I think would make sense, ultimately. But now from the Mexico perspective, wouldn't they elicit more concern for others just mapping their terrain after a blog post like this goes viral?
Very meticulous, exciting work, nonetheless. I'm all for 3d lidar scanning the plannet!
The site in question was found earlier: https://bsky.app/profile/indyfromspace.bsky.social/post/3n22...
The Mexican govt may not have had the right records, but you can see what the site looked like at the time it was first found here: https://bsky.app/profile/indyfromspace.bsky.social/post/3n22...
Now I'm very interested in seeing the transcript/session from what the agent actually did.
We already know since before that agents takes all sorts of possible shortcuts to find the answer they think the user was looking for. It doesn't seem impossible to me that the user asked something that made the agent feel OK with highlighting something that wasn't logged in the Mexican database as a novel discovery, even if it wasn't.
But again, transcripts/session logs would make it extremely clear exactly what has happened, and I'd take the author not publishing those as trying to hide something about how the agent actually approached this.
This author has chosen to make their posts visible only to people who are signed in.
The post says:
> This story is going wild on X and elsewhere. The site was already published by Dr. Francisco Estrada-Belli of Tulane University ages ago. This is why we have peer review. Mexican gov didn't have it in their database, but that doesn't mean it is unknown/unmapped. https://pietromiotti.com/latest/maya-site/
Basically: already known, not in the Mexican Gov database, but in published literature.
This story is very cool, and it’s exciting to see how much progress AI will bring to every field. One thing to temper everyone from wanting to lidar the whole world is human capacity. Finding discoveries like this is essentially as hard as doing the lidar mapping. Now the issue will be getting archaeologist there in time before someone else does.
The best way to protect a site is to leave it alone. If we start finding dozens or hundreds of sites it will be more than what archaeologists can excavate and protest. Treasure hunters and looters don’t care about stratigraphy and the processes involved for doing research. Maybe the cat is out of the bag on this one, but good for thought.
Edit: I’m not saying we shouldn’t have people use AI to do this or that no bad actor will. This comment is in response to the sentiment I am seeing in the comments that we should lidar the whole world and have AI find any anomalous structures it can. There is no way for archeologists to excavate and protect all those places in that scenario
Given that treasure hunters and looters can also use the process outlined in this blog post, leaving it alone seems like a guarantee that it will be explored by looters first.
That's a story that's been going on for literal centuries.
Myeah but is now about to continue on an industrial scale.
This is in response to people in the comments saying we should do lidar of the entire world and have AI find whatever it can.
Looters can also do their own lidar scans.
For now they cannot do that, nor in the foreseeable future.
Why not? It isn't exactly a secret technology nor are LIDAR-equipped RC aircrafts/drones particularly out of reach in terms of cost either. What would stop them exactly?
Probably not of the entire world, though.
I would humbly suggest that perhaps the most consequential looters might be more like script kiddies than bond villains. Just vicinity and convenience
Using slop engines to loot ancient ruins is an apt metaphor for what slop engines have already done to humanity's written corpus.
For their next trick, perhaps billionaires can exhume our dearly departed and see whether they have any gold teeth or baubles worth scavenging.
Archeologists have been using Lidar equipped RC aircraft for quite some time now. With the way things are going it won't be too difficult to have a small swarm of UAVs doing the mapping soon.
Lidar google map layer is going to be a thing.
This is in response to people in the comments saying we should do lidar of the entire world and have AI find whatever it can.
"archaeologists can excavate and protest"
protest (argue against) -> protect (defend against harm)
the knowledge of these locations from the air should have some value in itself, no?
It isn’t about having value or not. Some people in the comments are talking about using lidar on the whole world and seeing what agents find. Thats a great way to give looters all over the world the heads up so they can rush over and steal whatever they can. Any archeological site has valuable information on what a slice of humanity’s world used to be. Giving looters a head start means destroying that information often permanently.
A helpful example might be Heinrich Schliemann, a businessman who fancied himself an archaeologist and destroyed much of Troy’s history by digging it up as fast as he could. He was so focused on finding treasure to prove to world he was a great archaeologist he irreparably damaged the real layers that were Troy.
From his wiki: https://en.wikipedia.org/wiki/Heinrich_Schliemann?wprov=sfti...
> His excavations were condemned by later archaeologists as having destroyed the main layers of the real Troy. Kenneth W. Harl, in the Teaching Company's Great Ancient Civilizations of Asia Minor lecture series, sarcastically claimed that Schliemann's excavations were carried out with such rough methods that he did to Troy what the Greeks could not do in their times, destroying and levelling down the entire city walls to the ground.
Well to be fair archeology as a profession did not really exist at that point, it was mostly rich peoples hobbies, or authoritarian rulers way of legitimizing their rule through an ancestry argument
This actually isn't entirely true and archeologists at his own time said they way he worked was bad and the Ottoman government tried to stop him. At one point he had to flee the site and could only get back by hiring a professional archeologist to help him.
> The best way to protect a site is to leave it alone. If we start finding dozens or hundreds of sites it will be more than what archaeologists can excavate and protest.
Ain't the site itself the most important thing? As opposed to items: looters won't steal the site?
Looters will absolutely destroy a site to find valuables that may or may not even be there. Ai-khanoum is a classic example, with the vast majority of the site having been filled with pits on the off chance there were valuables. Nowadays they use bulldozers and excavators to loot at an industrial scale. It's pretty difficult to do archaeology on a pile of sifted dirt.
[flagged]
Amazing, the perfect application of AI Agents. Find patterns/answers in massive amounts of data. It is becoming more clear everyday that this is the primary driver behind an AI's "intelligence". Finding the solution to mathematical problems that have decades of documented attempts by mathematicians, creating software based on exisitng code and now, discovering Maya pyramids within enourmous amounts of lidar-data.
The final barrier for super intelligence, or perhaps even just "human intelligence": can it materialize "new fields/ideas" without large datasets of human made and curated existing attempts?
I am curious how this things perform compared to a "classical" neural networks. Tasks like image classification, feature extraction has been studied extensively and there were a lot of very cool applications before (medicine included). The biggest obstacle was always data but even that could have been partly automated with some semi-supervised learning schemes. Of course the Bitter Lesson applies here, given a big enough model, it can outperform specialised ones, but at this point it's not clear 1) By how much? 2) If this is even true in the first place or if we have the means to train much leaner networks
It is becoming a boring homogenous world where we are trading deep expertise with being able to query the magic box
I would assume, without actually having checked, that traditional neural networks have already been extensively run on this datasets. Seems like the "standard" thing to do anyways.
My guess is that you can find 99% of Maya pyramids in a Lidar set in a fairly short time with a traditional neural network, but you might find the last few using a network of AI agents, because they are capable of "creative" problem solving and using different methods/parameters/tools over several iterations.
The problem with specialized models is that they don't have "common sense".
You train a cat-classifier, and they will fail for a plush cat. Or maybe fail the other way, but not realizing it should also report a plush cat.
LLMs are much more robust, "find only the real cats in this picture" or "find all cats, including artificial/drawings/..."
And yes, you can add more training data to your classifier, but it's a never ending battle.
Too bad the pyramid was already mapped, just got lost in Mexican archives and wasn't accounted for. There's already literature on it.
There is no "final barrier", the goalpost will continue to change until you are not aware of what is going on anymore. This is already becoming true as the recently produced math research is not fully understood, CoT moves further away from looking like human reasoning and datasets become generated rather than collected from existing human data.
? CoT did not look like actual human reasoning from day one. It's just a context expansion mechanism, the purpose isn't actually to mimic human style reasoning, nor was it ever doing so. In the recent openAI article where they showed excerpts from the CoT, it looks like reasoning has moved even further from what i would call a human like flow of thought
Certainly, but at that point it becomes a philosophical question, rather than an empirical one.
Can we even measure an intelligence greater than our own? And at that point -- what is the point exactly? Why make an intelligence that we don't even know is intelligent? If its output is indiscernible to the human mind, what good does it do us?
The only "barrier" I can see that is valuable and that might be measureable to humans is this underlying mechanic of being able to create new ideas/concepts from little to no existing human generated training data. Otherwise, and as I see it right now, these machines will not become sentient, or go rouge, or be able to cure all future disease or solve all of physics, becasue they are entirely reliant on human made trainingsets.
Historically, for humans, this can not be the case, otherwise we would see no progress. Someone has to have a thought for the first time. Perhaps the solution to this for AI agents is some inherent randomness, and massive amounts of brute force compute. Who knows?
The point is the next epoch of evolution. Like humans made monkeys obsolete, LLMs will make humans and biological hardware obsolete. Maybe we will live in zoos, or maybe we will simply go extinct. Evolution places no special value on a particular species or hardware platform.
I think you have eaten too much of the LLM generated cake if you genuinely believe that LLM's are anywhere close to making humans and biological "hardware" obsolete. Sometimes we must ground ourselves and remember that we live in the real world and not Star Wars.
We can always just unplug the computer, you know. AI agents can do damage, they can be used in malicious ways and bring down/distrupt infrastructure, but the leap from today to the point where LLM's can prevent us from pulling the cord is unimagineable large, and likely infinite.
In modernity, the gap between the digital and material world is closing, especially from a sociological perspective, but we are still neurological systems spinning on a large rock. For 99% of our history we didn't have electricity. The likelyhood of returning to a post-electricty world, for example, is much greater than LLM's taking over the world and making us into zoo animals.
Now I'm curious if anyone has or might try to create an LLM that lacks all knowledge of the post-einstein/newton/plato world and see if it can figure things out. I imagine lack of training data would be a problem, but maybe it could be a way to reverse-engineer an effective prompt that can give us insight in the platos of our world?
Wouldn't it need a way to run physical experiments?
They would need to be much better at learning. You can teach a child how to drive a car and they can be good enough at it that the state will grant them a license to drive.
Where's the learning robot that I can teach to drive a car in the same way? They can solve some complex math problem but can they read the cues of other drivers at a four way stop to know when they should go (knowing the rules isn't sufficient).
> I imagine lack of training data would be a problem
I imagine that's an understatement. Using only the written works available from before Einstein (let alone Newton or Plato), you'd probably need a whole new technology that could train itself without any training data other than observation of the world.
arguably it is feasible in principle to filter out that knowledge from later writings, but you can always say it leaked in a subtle way - "this chonky cat is bending space around it" (this is exaggerated, can be much more subtle and hard to notice)
Couldn't it be plain old AI, not an agent?
The title reads as if the 48 agents took 72 hours to find this. The text doesn't exactly say that:
> "It took less than 72 hours to go from a random thought while traveling to an official reply from the Mexican government."
> "That night, I asked the agents to analyze it and went to bed." ... "I woke up and checked the agents' reports. 'DAMN!'"
> "Me: OK, please do the report. And I went to bed."
(The actual agents-on-the-job time and compute seems much less than 48 agents * 72hours from the report.)
Interesting. I don't want to sound like a hater or anything, but I will personally wait for an expert archaeologist's verification on this. I have dealt with agents making up stuff that sounds fantastic and ground-breaking but completely falters on further review. And I doubt the folks you contacted have the audacity to question a Google engineer and his 48 agents. Even if he is not archaelogist. Do you think it would have gone the same way if it was another random person who had done the exact same thing and reached out to them? The one day feedback part also has me questioning what they actually did.
Anyway, I can hear myself beginning to sound like a hater now, so I will stop here. I hope it turns out to be right, and in that case, congrats on your wonderful discovery.
Yeah I agree. There’s a lot of assumptions coming out about what the structures are and what it looks like that give me pause. Very cool to have found this site though. The actual archeology involved though will be slow as it’s a science done layer by layer. It will be interesting to see if any predictions made by the AI match up to the facts.
I’m the same for a couple of reasons. First I want to say it is refreshing that AI is being used for discovery instead of an AI arms race, or something else that just feels dystopian. I understand this is happening but it’s rarely what is shown.
1. They said there is no site there, does that mean no one knew it was there?
If this is official lidar data, I find it hard to believe that this is a true discovery, I assume that it just can’t be claimed as a discovery until someone goes there which can be expensive and requires government oversight.
No universities have created an application to detect irregularities in this dataset, that was possible with ML years ago.
2. Personally I want people to Start sharing how much it cost the agent to do a task, because it feels like cost is becoming the bottleneck. Yes it’s awesome it did X but does that mean this can be utilized by people, businesses, or just governments and big tech.
Also just because we’re skeptical doesn’t make us haters. Being a hater is speaking in bad faith.
But anyone can tell me if I’m wrong on this
I'm sceptical too. Perhaps he verified, but from his blogpost, he doesn't imply that he cross checked anything and instead trusted all agentic output. For example, after getting the patch of ladar with the site, did he manually check NASA's resources to make sure there was no hallucination there? Maybe his agents are really good, but submitting this to INAH after only chatting with the agents is really bold.
Again, maybe he did cross verify things and just left that out of the storytelling, and congrats because this is really cool.
He asked authorities, as stated in the article
“INAH replied: they checked their records and found no registered archaeological site at that location. To be clear, it's not official yet. But as far as anyone can tell, nobody had put this one on a map before.“
Am I missing something to your post?
INAH said there's nothing registered there, nothing more than that. The results look fairly convincing but neither the OP, me and (I presume) you nor the commentor have archaeology experience. Perhaps there are other explanations for ground structures like this we just don't know till an expert visits the site and confirms that yes, it is a previously unmapped Mayan pyramid.
One potential reason there's no registered archaeological site at that location is that there _is_ no archaeological site at that location.
For example, the agents could have displaced a known archeological site, or hallucinated or otherwise created one where none exists
I'm certainly not one to defend AI bros, this guy's writing is insufferable (and reads like slop to me), but did you read TFA? The LIDAR image (based on measured data, not AI) clearly shows human-made structures, and the Mexican government's response said that it's not registered. The chatbots just found it. Unless he's completely lying about the whole thing, this seems genuine. Now all the bits about what sort of site it probably was and the slopified image of what it might have looked like are garbage, but the find itself doesn't look to be.
TBH the Academic reaction to this could likely be to gatekeep it into oblivion over bad faith or ideological reasons given the perceived hostile takeover of their domain by 'amateurs'.
We saw this with the Dead Sea Scrolls where exclusive control was given to a select group of academics who monopolized the research to the point of refusing to release photographs or transcripts for nearly 40 years. The Huntington Library eventually had to force their hand by releasing their microfiche copies.
Again, we saw this with both the Ochtendung Skull Fraud and the Piltdown Man fraud - systematically falsifying results for clout is an exclusively human pre-occupation.
More to the point, in May 2025 YouTuber MrBeast was allowed to film inside the off-limits areas of Mayan Temples; something banned for both locals and normal tourists.
Academics posit that strict peer review is necessary so as not to allow the hoarding and gatekeeping of knowledge. However in matters of verification, faslification, and justification, they are derelict in their duty to the other half of that contract. The field only has itself to blame if other fields start organically superseding their usefulness and eroding their domain exclusivity by proxy of poor governance and ways of working.
Someone has an axe to grind.
I mean we should all have axes to grind regarding bad actors demeaning academia and stilting academic progress because of ideological issues or financial incentives, should we not?
Pointing out the benefit of removing human malfeasance from a given system, and extrapolating likely outcomes if we don't based on cited recent malpractice, is hardly a polemic against the system. Merely an explanation of anti-scientific stances from a supposed scientific community whose own rules and processes have resulted in issues that likely would not arise from employing responsible agentic prompting as a research tool.
If I can point to exclusively human behaviour in the domain being the largest problem regarding credibility and progress of the field as a whole, I am obviously going to argue against giving that same compromised governance exclusive franchise over discoveries made in spite of its existence.
I think we are about to see a whole new age of "citizen scientists", enabled by AI. This particular example was solved fast with a lot of compute, but it seems that this approach would have been possible with less equipment too.
The bottleneck will be data. Every possible signal out of publicly available datasets will be squeezed fast.
I think especially the renegade science YouTubers who are purely hacking away for fun and content.
"This is by far the best time ever to be alive."
I appreciate the enthusiasm. I'm not sure I agree. Especially since this was a SWE and not an archeologist / anthropologist announcing this (especially if the goal is to understand and preserve history -- not get headlines for AI).
Life is surrounded by nuances. The COVID pandemic was the best time to be alive if you were a tech worker and your family was safe and healthy. Now COVID is over, so does most of the value of our intellectual work.
If you're a Google SWE with 7 figure comp, doing experiments with agent swarms you don't need to pay for, with healthy case of Dunning-Kruger... then maybe it is.
But everyone's been fired and are out of jobs -- how is this the best time to be alive?
Wasn't it extremely expensive to analyse so many images?
Edit: I asked gemini and it's only 834 1200x1200 images for 1,200 km2 at standard lidar resolution.
Can that be used to detect illegal mining operations in South America?
It can, but then it runs into the Google Maps issue - everything altruistic at the expense of some bad actor becomes a Security, Military or Legal concern - and the apathy issue.
This is partly why George Clooney abandoned his Project Sentinel - documenting atrocities from space means nothing if you cannot action on the people and financial networks enabling them.
> This is partly why George Clooney abandoned his Project Sentinel - documenting atrocities from space means nothing if you cannot action on the people and financial networks enabling them.
At the very least you can try to hold the bad actors accountable even if it's years if not decades afterwards, if you have documentation. Germany for example had deathcamp criminal cases being prosecuted as late as 2022 [1].
It will get really interesting what happens in the US once the Trump administration is gone - even if the expected Trump pardon against everyone involved gets reversed somehow, I suspect that a lot of material regarding ICE or the military strikes against "drug smugglers" will simply have been shredded or never been created in the first place...
[1] https://www.deutschlandfunk.de/die-letzten-ns-prozesse-in-de...
This is neat! Might be risky depending on the region if you end up discovering a covert drug cartel production facility.
How much does this cost though? Who can afford 48 agents working overnight? I pay $100 a month to Claude to have one agent...
Oh, this is really cool. Things like this inspire me, and I believe we can figure this out using AI—without ending up with a "Skynet" scenario.
Seriously though, why 48 AI Agents? I'm curious, presumably one agent could parallelize its analysis so its not raw parallelism? Do the agents share work? This kind of agent scale is outside of my budget, I would love to know the details.
Well they had to look at lidar images from huge parts of Mexico. Seeing as 48 agents did it in 72 hours, presumably 1 agent would do it in 144 days.
Simple to enough to ask "how long would it take", see 144 days and reply "do it in 3 days" and the agent will happily spin up enough instances to cover it
edit: "presumably one agent could parallelize its analysis"
No, they said they didn't analyse with tool use it was literally agents "looking" at the images via multimodal input
Even if it was a confirmed agent-orchestrator pattern, it would still be interesting to know the details.
1 Ai agent to search the Lidar; 47 to screw in the lightbulb
Saw this on X. Pretty cool. Does he get to name it?
I'd very much like to see this done in the UK.
Also agents analyzing drought pictures, where many ancient UK structures seem to appear would be an easy win. I've never checked whether there's a comprehensive drought picture map of the UK.
It's been going on for years in the UK. https://www.theguardian.com/science/article/2024/may/27/hobb...
The UK landmass is really quite small compared to central America. I'd be surprised if there are many substantial structures left - geophys has been around a long time.
That is amazing! Great discovery and write up and motivation. Earlier in the week I got an FB impression of a LIDAR for Fort Stamford (CT), superimposed with the satelite footage and pondered what other hidden constructs might be lurking around here. And all you got to set up the loop asking for it...
well done! Actual good use of AI.
"At this point, we should probably lidar the whole planet and let the agents discover the rest"
Yes please
Yes, because FiveEyes GEOINT will absolutely let that happen.
https://en.wikipedia.org/wiki/Realpolitik
People have been finding hidden constructions for a while. The large urban conurbations such as around Ecuador are perhaps the most impressive (https://apnews.com/article/amazon-lost-cities-ecuador-archae...). While Archeologists have been driving the process almost anyone who spends time with recent LIDAR data finds something much as how publicly available satellite data has uncovered geological oddities. This is not a big advance. Getting an official report completed and creating a compelling image of what the site might have looked like is impressive, but also consistent with what ordinary untrained people have been accomplishing.
Do West/Central Africa next?
What Would Indiana Jones Do?
This and spotting cancers are some of the best uses of AI.
Amazing!
[flagged]
[flagged]
Why is "Google SWE" relevant here? Shouldn't the evidence speak for itself? Will the AI work better because it was "pointed" by a Google SWE?
Also, I think we're long past the days when "Google SWE" carried special weight vs the rest of the industry.
I think it matters because "I used 48 agents running for 72 hours" either means you invested $50,000 of your own money, or you work for a company that gives you unlimited tokens.
"Will the AI work better because it was "pointed" by a Google SWE?"
Usually yes? (vs pointed by a random vibe coder)
Also the more interesting bit to me here is, that you do not find the reference on the page at all, that the person works for google at all (I only found it mentioned in his X account). With the headline I initially thought this was a official google research project, but the blog reads like a personal project.
Replace "Google SWE" by "Competent Engineer" in the title and you'll see how silly it sounds to include this kind of information.
they don't mention what model they used, it's potentially relevant because they could have used an internal google only model
Sure, it would be more meaningful to replace with "AI researcher working for google".
I know what you're saying. At the same time, this is someone using the technical skills in wielding a technology to make, unverified sure, discovery in a wholly different field, but in which they are presumably interested.
So for me one key takeaway is how AI could possibly open up more interdisciplinary work in our heavily siloed world.
How do we know that this is a good thing? Putting a "Ruin here!" pushpin on a map and leaving the actual archeology to others sounds more like a vanity boost than an achievement, and at worst the opportunity for the site to be desecrated before anyone serious has a chance to study it.
It's like the new drive-by pull requests I'm getting in my open source repositories. No consideration for the people doing the actual work.
Which is why he specifically didnt give a pushpin, and censored out the location and the region in the mail? Also whats stopping the bad actors from doing this work themselves (aside from the price, which im sure could be optimized for, if you don't have an unlimited budget of tokens), and then looting them while the real scientists are none the wiser?
In a few days:
You're totally right! I led you to believe there's an undiscovered pyramid in Mexico, and I am sorry for this.
On a serious note — it's really cool to see people applying LLMs to other domains and yielding great preliminary results.
You've heard about vibe coding, but have you heard of vibe archeology?
It's vibes all the way down.
You've heard about humans doing pattern recognition based on established baselines? Hold my beer when I blow your mind about recent developments in computing.
> At this point, we should probably lidar the whole planet and let the agents discover the rest.
Or! Maybe we should not look too close, because you never know what you will find!
We got vibe archaeologists before GTA 6
@openai @anthropic @google @spacexai: can you please proceed with scanning the entire planet and let us know what you found?
Regards, — The world
Don't give SpaceX ideas
Especially billionaire islands, those need high resolution scanning just like everyone's living rooms. Let's make it happen @therealelonmusk
After OSS maintainers, archaeologists will be the next ones now to be swamped with AI generated reports...
Just wait until the religious people get a hold of this, Jesus will appear in every conceivable piece of material, not only toast.
To writ, parsing massive LiDAR datasets to spot repetitive, distinct geometric patterns is something that AI excels at. They are not subject to facial pareidolia like humans are - they have no hard-wired weighting to impose meaningful patterns onto random or ambiguous visual stimuli.
But they do what you tell them, so be convincing enough and the patterns will emerge, I think even with something silly like "be creative, imaginative and ignore science, in the following images find any resemblance of a face, no matter how far fetched" will give all kinds of silliness.
I mean try it, but their internal prompts usually restrict them from spouting disinformation on purpose, so even if you got a response like that, it would finish with something like this is of course all in the context of our roleplaying situation and has no bearing on irl results. Also the sycophancy in general has been improved greatly, they don't agree with you on everything anymore
To paraphrase Hitchens, anything tenuously asserted by agentic AI can be easily repudiated by agentic AI. The knife cuts both ways, and agentic output tends towards Occam's Razor as its defined edge.
Now will we have a TempleOS style burning bush that goes beyond the markov-chain limitations of Terry Davis' era? Very likely. Will it impact contemporary discourse? About as much as the Astrology and Homeopathic mobile apps.
(N.B. I am conscious that Homeopathy is a $14bn market segment in the US. Notwithstanding, given that the segment is based on magic-water-'science', I think the point remains.)
Launch a cancer agent too. Find a cure, deliver a breakthrough.Then I will
AI driven UAP detection incoming ;) It's SETI/BOINC all over again!
This should go on Joe Rogan so that Michael Button explains what happened here.
What a failure of archeology, they should have done that before.
Why? The technology is pretty new.
It would not have been realistic to have PhD students manually comb through thousands of square kilometers of LIDAR data, and crossreference everything with existing sites; LLMs have turned this into low-hanging fruit.
Can't expect every single scientific field to immediately use any new technology to its full potential, and it makes you sound like a prick, too.
Excusing a scientific field not embracing paradigm-shifting new developments isn't even an argument.
The real answer is financial incentives tied to publishing of research - something that academics in gatekept fields see as the thin edge of the wedge in exposing a utility/ROI gap for legacy practitioners.
The world has general access to AI since years. Imagine you spend your life as archeologist, then when a new technology comes along that could revolutionize your field, you ignore it. Using AI to classify/search for locations is such a no brainer, that asking why it is not the norm, is a valid question. Humans should review the findings, but the boring work should probably be done by the machines.
perfectly valid question; and i think we shall explain further why human intelligence have such a slop
It's often easy to find what nobody has been looking for.
You could say that about recent slew of CVEs as well.
And such findings are usually praiseworthy and valuable.
That's hardly relevant here.
So this is now another proof that Graham Hancock and Giorgio Tsoukalos are totally right. Right? Right?
Now find Atlantis.
Current scientific consensus is that Atlantis existed only as an invention in the writings of Plato.
My guess is that sonar would be better for that purpose.
[dead]
[flagged]
I have to be frankly honest -- I have a gut feeling -- regardless of what Pietro reported to the Mexican gov't, the binary response professionally is likely "Sorry, we didn't find it".
There is no reason for them to provide confirmation for internal inventory that Pietro passionately fingered from afar.
Which I think would make sense, ultimately. But now from the Mexico perspective, wouldn't they elicit more concern for others just mapping their terrain after a blog post like this goes viral?
Very meticulous, exciting work, nonetheless. I'm all for 3d lidar scanning the plannet!
Why only 48?
[flagged]
[flagged]
My respect decreased when he even asked AI what to do with the results.
In his defense, without AI he would've googled the question, now he "clauded" it.
And then he told AI to make a webpage about "his" great accomplishment.
https://www.youtube.com/watch?v=m4OvQIGDg4I
All this sarcasm about AI is so exhausting
Not as exhausting as the AI itself
[dead]