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...

To some extent it's still an interesting result: an independent validation of the original finding, and a proof of concept that this technique could make such a discovery.

IF the llm did not have the paper on it's training set. Which we do not know.

Here is the referenced publication. Pages 13-14 show the structures. https://www.sciencedirect.com/science/article/pii/S2352409X2...

This is a good example of the difference between an LLM providing a theorem and a person deducing theorem, and all the juicy knowledge we get from truly understanding things: the Google SWE found something he thought was undiscovered. He asked AI to make an image what it might've looked like and speculated that it was used by the local elite.

But Dr. Estrada-Belli found something that was undiscovered. Finding this structure wasn't his number one goal - it was the side effect of a larger anthropological assessment that allowed him to improve estimates about population density of the north versus south, how Mayan homes and farms are distributed, what this means about social relationships between the elite and common people, how different regions were interconnected, etc.

Interestingly, one of Dr. Estrada-Belli's primary conclusions is not that these structures were only used by "the local elite," but that the closeness of residences and farms to these community sites suggests that the elite and the common people actually had a much closer and nuanced relationship than we previously thought. That's the opposite conclusion you'd get from the Google SWE's assessment.

Knowing that a Mayan site exists is one thing. Understanding what it means is another.

IMO, his primary mistake was not turning the agent swarm on a proper research task that exhaustively determined whether it had been discovered or not.

Well the Google SWE didn't make a mistake, the media made a mistake in misreporting it, and we at HN are making a mistake by giving it undue attention.

We are reading this article because it continues and amplifies the AI hype machine, and no other reason. If a motivated amateur had made the discovery through any other means, and motivated amateurs do things like this all the time, then it would never have gotten an article, never shown up on the HN feed.

Very reminiscent of my experience pointing persistent agents at computational physics problems. It can find amazing results and really surprise me, make a write up, and convince me it's a real discovery... until i tell it to do a literature search, and be meticulous. Then it comes back saying "prior art has reduced the novelty of the discovery", and finds papers explaining the discoveries very easily and intelligently.

Perhaps google SWE should have requested a literature search before publishing his results as novel

Lets take a moment to consider why that has started happening.

The lineage of every LLM of relevance today was the largest theft of intellectual property in human history. Every digitised creative work, whether in the public domain or not was taken, often outright pirated, with the explicit intention of being able to trivially produce compelling forgeries. Physical works are being enthusiastically destroyed to digitise them to further feed the hunger. And outside of a few court cases, the original creators across the world have been paid nothing for their work having been stolen and repurposed to put them out of a job.

Meanwhile, those same digitisation efforts have resulted in badly behaved scrapers from all comers absolutely thrashing the entire web, in many cases exponentially increasing the cost of hosting for smaller entities. Larger entities care less about that but are still enthusiastically walling their gardens so they can monetise the output of their communities rather than continuing to allow it to be stolen freely.

We are siloing our knowledge out of desperation. I'm sympathetic to the idea that knowledge should be free but that isn't possible when bad actors like Google and OpenAI are preying on the commons.

From my perspective, the bad actors are the corporations and greedy people who turned copyright into a perpetual rent on IP. If copyright terms and IP laws were reasonable, I'd be 100% with you. But the idea that a novel written in 1940 is still not public domain, just so the heirs (or more likely, corporate purchasers of the rights) can continue to profit on a work that was itself but on the shoulders of thousands of years of civilization? Screw that.

The Walt Disneys of the world screwed themselves on this one. If copyright was still the 20+20 it started as, and if the bulk of people being "stolen" from (don't get me started on using theft to refer to IP), then I think most people would be much more up in arms over the AI industry.

But, in a world with sane copyright laws, perhaps AI companies would have different approaches. Today, if they want anything after 1930, they're either breaking laws or in uncharted territory.

And siloing our knowledge is a silly response even if you are a copyright maximalist.

Theft/stolen implies it's been taken and the owner deprived of it. Pirated or copied is more appropriate, but still not quite exact as it's been encoded into what amounts to lossy memory. If I ask a person to tell me about a paywalled article, they'll share what they can remember and likely get some facts wrong. An LLM is the same (these days; GPT-3 was another story).

I do agree that the methods of obtaining much of the material (eg. the published works torrents) were stupidly wrong and they should pay for that. However, legally acquired media being "read" by the training process isn't so different than it being read by a voracious reader: it's lossily encoded in (what amounts to) memories.

The insane scraping levels and behaviors ... not wrong. If only there were companies who already did that responsibly they could contract with for data. Hmm. (But they have to "own" it, as is the SV fashion these days.)

Not we, just Elsevier. As long as Academia sells its research, information will not be free.

AI is already fully capable of solving the majority of/all captchas, you just aren't supposed to do it due to TOS.

I expect with time these kinds of things will change.

Who says the agent was treated the same as you?

If the "AI" scrapers honored HTTP 402 I'd be happy to let 'em in.

Or necessarily depending on your viewpoint.

Did his Gemini AI agents just use Google search, find the publication, check the coords, and claim it as a discovery? Ha

Clicked the GP link and I got a “this post is private” page. Clicked your link and got a Cloudflare page that hangs and I can’t move past. That’s the Internet in 2026

> I can’t move past

Come on, George, you're clearly a ramblin' wreck from Georgia Tech. You've taken nearly every course GT has offered over the past century, you can get through a captcha. Live up to your name.

>remote sensing is difficult and any archaeologist knows to triple check before saying something is "new"

>Francisco was very kind and shared his publication image with me

...can she post the pdf?

Seems likely the google SWE that wrote the blog wouldn't have claimed this was new if there was a public way to access this information. I understand archaeologists have valid reasons to keep location details private, but complaining the OP didn't "check" thoroughly (when she can't link to the data he should checked in order to validate it was new) reads more like a shortcoming in how this knowledge is shared than a failure of OP to check.

open access.

https://www.sciencedirect.com/science/article/pii/S2352409X2...

Not to agents

I told my agent to bypass Cloudflare captcha's and it happily did so.

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... and open-access.

Link to the previous publication: https://doi.org/10.1016/j.jasrep.2025.105288 (Journal of Archaeological Science: Reports 66 (2025) 105288)

> Me: That's awesome! Please check which of these villages haven't been discovered yet. Search both the literature and the archives.

> Agent: One major village doesn't seem to have been registered.

The idea of just brute forcing discovery with agents on lidar is really cool, but doesn't the story ultimately rest on the agent making a mistake in its literature search?

Yes, and I think this point and the post you're replying to are the central fact of this story, which the OP should acknowledge.

My own attempts to use agents to develop new historical knowledge [1] point to this as being both a very promising and interesting domain, but also one where the agents reliably and repeatedly make claims of novelty that are based on having read ~80% of existing research. Obviously to make an actual well-grounded claim of novelty you basically need to approach 100%.

This is partly why math is so tractable for this sort of thing - mathematics papers tend to be publicly available and searchable, whereas for history, it might be the case that you have an agent swarm duplicating a find that some French person in the 1870s previously reported in an obscure undigitized book.

[1] Detailed more here: https://resobscura.substack.com/p/using-opus-55-to-discover-...

you can see they're obviously the same structures in the images. just search for the author and you'll find the paper.

The approach did work, but the discovery isn't new. Independent re-discovery happens all the time science.

but the paper was probably in the AIs training set and they could have accessed it at any time during the run.

Yes but someone who knows what they are doing with years of experience i the field probably slows down, is more thorough, and goes through a peer review process before rushing to announce to the world their new discovery.

The moral of the story is that if you thought you found something that was undiscovered: no you didn’t.

BUT, if AI thinks it’s undiscovered then its discovery might be poorly documented, so if you were to go to the site by yourself you might be able to explore it on your own and raid tombs, etc, and no one will notice.

Tomb Raider is a video game.

In real life, that’s actually just vandalism of an archeological site for personal gain.

Potato, po-tah-to.

Don't ruin Indiana Jones for me.

even if it was discovered, I'd say most of the accolades go to NASA and LIDAR, the fact that AI agents were used to discover it isn't a big deal.

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.

> That is an irrationally cynical take. Everything described in the post is clearly within the abilities of a frontier LLM.

No, the burden of proof that it's actually novel sits on the author of this post, and we assume everything is cheated/shortcutted by default when it comes to agents and LLMs, unless we can prove it actually "found" this, not just looked up stuff that wasn't properly in the DB yet but already written about.

> The reasonable interpretation is that the model stumbled upon a previous discovery in the manner described

That'd be reasonable indeed. Instead the author chose the headline "My AI Agents Found an Unmapped Maya Site" and the first sentence is:

> By analyzing NASA lidar data, my AI agents discovered a Maya site in Mexico that, as far as anyone can tell, no one had reported before

Which without any evidence of what the agent actually did, I don't think we should just assume what the author says is true because again, we know that agents takes as many shortcuts as they can.

Plenty of times the people pushing LLMs are over-exaggerating more than in other ecosystems, and the community should rightly push back on these things, when they're not presented properly with proof and evidence. Otherwise we'd be doing previous actual archeologists a huge disservice.

Imagine being the archeologist who actually discovered this site, and waking up today reading some random person taking credit for your discovery! Kind of feels like people here often forget there are other people involved on the other side of things.

So now this apparently amazing feat that was rushed into publication is actually just an out of date DB.

Peer review also protects the authors for making a fool of themselves. QED.

Looks like it was peer (or rather superior) reviewed. I don't think the author was trying to be malicious and just wanted to blog about something cool they found.

That is not how peer review works typically, but at least the guy did try to confirm with actual experts. So no, no evil here.

I don't follow, what exactly are you saying? Are you claiming that a scientific article (shared in a sub-thread alongside yours) is fake?

That's a pretty extraordinary claim.

You need a shave, here, use Occam's razor.

Thanks for your reply, but I withdrew my original comment.

With respect to your reply: https://youtu.be/klbw3pVnba4

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.

Probably not of the entire world, though.

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?

With this you are searching for a needle in a haystack. There's a whole bunch of jungle to cover. With a drone you would spend ages not finding anything due to their limited range. That Would be pretty bad ROI.

Also, drone mounted LiDAR is often not powerful enough to go through dense foliage which you have in these tropical climates.

Ok, those are all reasons why it's hard, which it is for everyone by the way, not just "looters". It's still possible and doable, like it is for others. Your previous comment made it sound like it was impossible specifically for looters for some reason, which I'm glad we've cleared up wasn't your intention, thanks for explaining!

I would humbly suggest that perhaps the most consequential looters might be more like script kiddies than bond villains. Just vicinity and convenience

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.

Well isn't it handy that recording lidar is really expensive, so we luckily won't be having large scale public access to data very soon

> 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.

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 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?

There are other authorities! Such as researchers, academics etc.

See: https://news.ycombinator.com/item?id=50453616

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 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 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.

It does seem amazing how mountains of evidence have to be assembled to disprove academic narratives the whole field defended for decades, even if reports from the time gave us proof hundreds of years ago. Things like the massive human sacrifices that were made (usually by colonized tribes, not the ruling Aztecs) on a systematic scale are basically an anti-thesis to the current national narrative of the state of Mexico itself.

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.

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.

You are right and I get the point (I have also worked on some solutions, though it's not my expertise), it's just that usually the people creating the ML model are supposed to substitute the creativity that the model itself does not offer. You run the model, see the false negatives and start thinking of what is missing, if there is also information that can be represented differently or can be compressed, if there is some other approach entirely. Good ML ultimately requires having deep expertise of your domain and can sometimes lead to deeper insight.

With LLM you unlock a whole new world of possibilities regarding the speed and result but we are also finding ourselves in a position where "asking the LLM" because the cheat for everything, no reason to dig further

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)

Too bad the pyramid was already mapped, just got lost in Mexican archives and wasn't accounted for. There's already literature on it.

Couldn't it be plain old AI, not an agent?

What kind of harness setup that would allow me to fire off a prompt, go to sleep, and wake up to see such a comprehensive and intricate infra setup (48 agents, orchestrated, image storage, continuous execution), and just say “damn”? I paid my for peasant $20 bucks a month plan and works in the CLI (Codex), I never know how to scale work on number of agents, non-interrupted workflow, or multiple models (he mentioned he consulted multiple models, I assume not just copy pasting questions in different chats). Is there a harness that I’m missing out on?

I highly recommend pi.dev for doing anything creative with agents and harnesses. It separates the harness from the model, so you need to BYOM keys and subscriptions.

You can build your own harness quite easily or use a harness something like pi.dev which offers a lot of flexibility in customization in terms of tools, models ised, resume sessions at a prior point in time, etc.

I have used pi.dev to easily start from a known context and goal and use it to compare the cost effectiveness, token isage, etc. of different models to reach the goal state.

I am sure there are many ways to do this successfully.

Type into claude code:

"Scan through publically accessible LIDAR data on <region of mexican jungle>, search for potential Mayan ruins and cross reference with published data to rule out existing finds

Work autonomously until the entire area is searched, prepare me a report detailing potential discoveries"

should more or less do the trick

"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.

> Now COVID is over

Ask anybody with newly acquired Long COVID / PASC if COVID is over.

https://www.thegauntlet.news/p/how-the-press-manufactured-co...

By that logic, not even the Black Death is really over.

That makes no sense. Sorry you succumbed to the aforementioned propaganda.

How does it not make any sense? there are 1-2k cases of bubonic plague reported per year in the world

Long COVID is vastly underdiagnosed.

"Life is surrounded by nuances".

Sure. I agree. But the statement I was responding to was not nuanced.

But when was the best time, then?

From a global point of view, we've been living in relative peace for almost 100 years.

Housing is a problem, but child mortality isn't. Tech overlords are a problem, but no one is testing a nuclear bomb every week. The Koreas are still technically at war, but tuberculosis deaths have plummeted over the last century. The Cold War is over, but people are still dying in wars around the globe. US imperialism around the world is finally showing signs of decline, but now China manufactures practically everything, and other developing nations are struggling to compete.

It's always the best and the worst time to be alive somewhere in the world. It's up to you to decide what you want to make of it, anyway.

That line also made me do a double-take. No doubt this is cool and all, but that's a strange blanket take away.

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.

This post turned out to be a perfect example of the blind faith in LLM agents. Their outputs are not to be trusted and must be rigorously checked.

I don't see how the post displays blind faith. The author contacted the relevant authority in Mexico to ask if they already had a record of this village, and even after they said that they didn't, he was careful to hedge and not to claim that this was definitely an original discovery. He flagged the speculative part of the post as speculation, and as far as I can tell, the parts he was confident about have not been disputed.

Doesn't matter, the title is out there, news outlets will omit this little detail. Even here the post is gaining in popularity even after the top comment has questioned its validity.

The AI craze is quite possibly the most annoying hype cycle I’ve ever witnessed.

And what exactly would that rigorous check be?

You pull up the lidar scan and see that there actually IS what clearly appears to be a human-made structure.

And he did. And there is. And then he rigorously contacted government authorities and verified that it is not a registered site.

There are other problems at play. But this is not one of them.

it feeds into the typical egotistical nerd fallacy of "im smart in X, that translates to be smart at almost everything else with lower effort".

I myself have to keep my stinking paws from some projects at work due to realizing that AI was making me believe I could shit taller than my ass.

It's like revenge of the nerds, but this time the other nerds outside the AI craze are the target instead of the typical bully.

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.)

Given that we can all see the mapped pyramid in the previously published paper https://www.sciencedirect.com/science/article/pii/S2352409X2..., the title of this seems incorrect ("finds unmapped Maya pyramid").

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.

> The bottleneck will be data. Every possible signal out of publicly available datasets will be squeezed fast.

Exactly. The only blocker to us pulling this off ourselves is access to the LIDAR data.

You CAN just do things, but one should also temper the excitement a bit. Agents are amazing but also the last 10% is still really difficult to get right and requires subject matter expertise for most things.

As an aside: anyone with access to all those tokens for funsies can do this. Folks without that access cannot just do things. The have / have-not of tokens will be interesting to see over time.

Ha, yeah I had the same thought. People with money to burn have always been able to “just do things”. The author also considered “hiring a survey team” - ultimately concluding it was too expensive - but the fact that that thought even entered their mind indicates a certain level of expendable income.

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...

Cool story but:

> They turned the 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 while filtering out natural hills, sinkholes, and roads. There was no special model or classifier involved: the agents literally looked at the pictures, following a precise guide.

Would it be better to ask a single LLM to create a processing pipeline to inject raw LIDAR data, create a heightmap and use an image classifier to identify unnatural shapes that standout and create a ranking score with a higher value where multiple shapes appears close to each other. At least you get something reusable and probably multiple order of magnitude faster.

For all we know, that's exactly what the agent did.

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.

How much does this cost though? Who can afford 48 agents working overnight? I pay $100 a month to Claude to have one agent...

If these type of subtle finds interest you, this account is great: https://x.com/MoundLore

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...

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

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.

The National Library of Scotland has LIDAR imagery for all of the UK. Go to https://maps.nls.uk/geo/explore/ then pick a LIDAR layer as the background. This motivated me to make my own high-res LIDAR images on my hobby site (https://solentmaps.uk/) of my home area using QGIS with free government data in order to uncover interesting things. It has old OS maps of the UK (1880s to date) with a LIDAR layer for my local area (south Hampshire).

I'm far less interested in LIDAR as it relies on height change. The drought pictures are a better source of new discovery in the UK as we tend to bury buildings or plough over them (see my other comment below).

Those pictures would be very appropriate for AI bots to look at and make discoveries.

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.

Well, that's why I explicitly mentioned the drought pictures - LIDAR uncovers structures due to change in the terrain height once vegetation is 'removed', whereas drought pictures are grasses growing poorly on top of buried structures or their foundations. That's a very UK/European thing where a lot of the history has been covered up or ploughed over.

Just near me, a Roman road about 5km long was discovered last year by exactly this method. That's a non-trivial discovery. There was also a large Roman villa complex discovered the same way.

For LIDAR and structures, you're likely correct - there's vanishingly obvious structures left to discover that way.

https://www.bbc.co.uk/news/uk-wales-52911797

"Roman forts, roads, military camps and villas have been identified by a new analysis of aerial photographs taken in the 2018 heatwave across Wales.

Scorched crop marks uncovered about 200 ancient sites during the drought.

Experts say the Roman finds are key pieces in the jigsaw to understand how Wales was conquered and dominated 2,000 years ago.

Researcher Toby Driver said the discoveries "turn everything we know about the Romans on its head"."

This is neat! Might be risky depending on the region if you end up discovering a covert drug cartel production facility.

well done! Actual good use of AI.

This is probably one of the coolest AI related news

"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

Saw this on X. Pretty cool. Does he get to name it?

HEllo

The title is "My AI Agents Found an Unmapped Maya Site"

Do West/Central Africa next?

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.

This and spotting cancers are some of the best uses of AI.

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.

> Why is "Google SWE" relevant here?

Because it did not work the first two times this was submitted without mentioning "Google SWE": https://news.ycombinator.com/from?site=pietromiotti.com

So I guess our revealed preference is that the outputs of AI prompts are objectively more interesting if the prompting is done by Google SWEs.

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.

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".

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.

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?

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.)

You've heard about vibe coding, but have you heard of vibe archeology?

It's vibes all the way down.

@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

We got vibe archaeologists before GTA 6

> 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!

Launch a cancer agent too. Find a cure, deliver a breakthrough.That will be impressive

AI driven UAP detection incoming ;) It's SETI/BOINC all over again!

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.

perfectly valid question; and i think we shall explain further why human intelligence have such a slop

Are you under the impression that this finding will revolutionize the field of archeology?

Enjoy calling other people failures much? https://www.sciencedirect.com/science/article/pii/S2352409X2...

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?

Amazing!

> You can just do things.

I’m sorry, but you didn’t do much. The work was done by clankers.

Now find Atlantis.

It's relatively easy to find on the free streamers. For instance Pluto airs it on the Stargate channel.

My guess is that sonar would be better for that purpose.

Current scientific consensus is that Atlantis existed only as an invention in the writings of Plato.

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!

All this sarcasm about AI is so exhausting

Not as exhausting as the AI itself