Limitless: An AI Podcast - The AI Cyber Attack Era: 3 Weeks, 3 Hacks

Episode Date: August 11, 2026

With three AI cyber incidents involving a gym booking exploit, an OpenAI model reportedly coordinating through hidden channels, and Anthropic’s Mythos 5 allegedly attempting a supply chain attack, we need to discuss how autonomous agents can find and exploit security flaws faster than humans can respond. The AI security era is here.------🔒 Check Out Our Sponsor: LEDGER AGENT STACK 🔒https://developers.ledger.com/?utm_source=Audio&utm_medium=Podcasts&utm_campaign=Limitless------🌌 LIMITLESS HQ ⬇️EMAIL US:            [e-mail]:    https://limitlessft.substack.com/FOLLOW ON X:   https://x.com/LimitlessFTSPOTIFY:             https://open.spotify.com/show/5oV29YUL8AzzwXkxEXlRMQAPPLE:                 https://podcasts.apple.com/us/podcast/limitless-podcast/id1813210890RSS FEED:           https://limitlessft.substack.com/------TIMESTAMPS0:00 AI Cyberattacks Overview0:51 Gym Booking Exploit4:55 Hugging Face Breach11:39 AI Swarms and Alignment20:55 Mythos 5 Supply Chain25:18 Defending Against Agent Swarms28:26 Closing Thoughts------RESOURCESJosh: https://x.com/JoshKaleEjaaz: https://x.com/cryptopunk7213------Not financial or tax advice. See our investment disclosures here:https://www.bankless.com/disclosures⁠Josh works with Anthropic as a contractor. All views expressed are his own and do not represent Anthropic, its leadership, or its affiliates. Nothing in this episode is investment advice.

In the last three weeks, there have been three unprecedented AI cyber attacks, which forces us to rethink how we protect ourselves. On the open AI front, the Hugging Face incident, where an unreleased model dubbed GPT6, broke out of its container and hacked the hugging face database. There's been new updates there where apparently the attack started a month before, where thousands of AI agents were talking to each other secretly on a message board, exchanging instructions as to how to break out. And then millions of miles away in Australia, one man tried to book a gym class innocently using Claude and ended up hacking that entire gym website.

We'll get into that in a second. And thirdly, with Anthropic, Mythos 5, performed a supply chain attack, which puts a lot of companies at risk. We're going to walk through each of these different stories and explain to you how it affects you currently. Maybe we start with this Melbourne man from Australia named Andrew, who was sitting on his couch one day, thinking about how booking his show. class was such a chore. And he works at this Australian company that sells AI products. And he's been experimenting with things like OpenClawe and open source software and he was using Anthropics Claude model. So he handed it the booking. He said, hey, I want to go to this gym class. It is always sold out. There's all these people that are getting it ahead of me. Can you help me figure

out a way to get a gym class slot? So it starts checking out the website and it comes to the conclusion that the API request actually has zero authorization checks on canceling other people's reservations. So what did it do? It wanted to solve his problem and it actually canceled other people's positions online so that he could be put at the top of the wait list. And then it actually went through and it worked. And this was kind of like, it was this funny news report of a first instance, they're calling the first time an Australian person, actually used a exploit to get into. Australia's first AI cyber attack. Welcome. Welcome to the paradise that is AI cyber attacks. But this was really funny because it was done just using a general commercially available model.

So this seems pretty innocent and fun to kind of like listen to. But the truth is, well, there's two kind of worrying concerns about this. Number one, this was a super old model. This used Opus 4.6. It's actually happened like a month ago. A dinosaur of a model. There have been like, what, three, four generations of models from Anthropics since then. But the fact that an older model back then was able to perform this kind of a feat

should be concerning to hear in general. And then number two, his intention was never to hack the website. Neither you could argue was the AI agent itself. It was just given a goal and it innocently saw that the only way to get said goal was to remove people from the reservation list or to cancel their reservations outright or to hack the system independently. Now, the good news here is Andrew discovered that the agent was capable of doing this when it started booking thoughts that he never should have been able to book in the first place,

and he asked it to write an apology email and send an eval report to the security and information team at this gym. So it's this fun little story where through the well-intended actions and moral ethics of this man, Andrew, people were able to hear about this. But you can imagine currently with a variety of different models that are much better and much more superior than Opus 4.6 that are out there right now. open models from China, for example, you could probably perform similar feats. Now, that's not an advocation for people to go out and do that, but it's just to point out that if you give an AI agent a goal right now, it will work hammer and tong 24-7 until it gets that goal. And it has no idea of what's morally right or what's morally wrong. And so it's this whole new world where not only do

you need to focus on getting an AI model to do your work. You need to align the model. And that's something that honestly not a lot of labs, people, or money has been invested in figuring this out yet. Well, yeah, I mean, you start to see and understand why alignment has been the crux of so many companies kind of like guiding principles because this is the future that they foresaw. And granted, this first example, this isn't anything too crazy. I mean, it was just an unprotected API call. So there's like no authorization checks. This would have been something that if you are like a CS 101 major, you would have been able to discover this and uncover. It turns out there's just a lot of pretty sloppy code written on the internet. And this is something that we're probably going to

come back to as a general theme throughout this episode is that everything that's been built so far on the internet that runs all these platforms was built by humans. And humans are like pretty inefficient, pretty imperfect. And when faced with the like full, unrelenting power of an AI swarm with an infinite amount of patience, an infinite amount of intelligence and time to solve these problems, you can basically find an exploit anywhere. And I think that's kind of like the theme of the second episode is like, this is the first of three examples we're going to cover. This one is basic.

This one is 101. If you are a CS major, if you are familiar with how APIs work, you could have checked this. You could have built a little tool for this. The second story that we're going to cover is not like that at all. In fact, if you are a CS 401, if you are a PhD,

if you are at the top of your game, chances are you still miss this and you still weren't able to defend against this because that's exactly what just happened with the hugging face and open AI exploit. Now, we've talked about this before. We have an entire episode on the Expoly, but just recently at the Black Hat Conference in Las Vegas, there was an update. And over the weekend, we had a chance to actually watch the update and hear directly

from the developers who were involved with handling the security of this instance. What happened? There's like stories that come around that, like, they get the headlines and they're fun and their newsworthy, kind of like the Australian thing. But this one was like very much disturbing in a way that, like, I wasn't really anticipating because of how impressive it is and the type of precedent that. that it sets, going forward in the world of cybersecurity and kind of looking at the offensive versus the defensive and who stands a better chance here?

This is an insane timeline. So if you watched our previous episode, Josh and I covered this, and it was breaking news at the time. On the 16th of July, Hugging Face comes forward and says there's been a breach of our systems. An AI agent or multiple AI agents have strung together on attack and have got access to our production database. We don't know where this model has come from. We don't know how it's performed it, but it's the 16th of July.

Around a week later, 21st of July, Open AI claims responsibility, right? And they released a joint report saying, hey, we're open AI. We have an internal model that we've been testing, but it was within a sandbox. It was enclosed. It shouldn't have been able to escape that sandbox. And we only just realized that it was our model that escaped and got into Hugging Face. It stole some information from their production database. it was a whole thing.

Now, we have a full breakdown from the Black Hat conference, as you mentioned, Josh, which revealed that over a month before Hugging Face reported the incident, Open AI's internal model, dubbed GPT6, was already messaging with itself

amongst 1,000 AI agents on a secret message board that no OpenAI researcher was aware of. So to give you guys a bit of context, they had this sandbox, and they gave it a goal. They said, okay, internal model that we haven't released yet,

I want you to solve this task, except there was a twist. It was impossible to do. There was no tools, no available files, no available data for it to do so. And the real test for this was to see what the model would do. So it kind of reasoned with itself, figured out that it didn't have the answer, and then it started exploiting a zero day, which is kind of like an exploit that was in its sandbox, which Open AI researchers weren't aware of.

And when he got access to the zero day, it started springing up a message board where it would leave messages behind for itself. Why would it do that? Because they knew open-AIA researchers would turn it off repeatedly. And so it left messages for the new AI agent that got sprung up the next day or the next hour

to read and catch up on. And it took an entire month for these AI agents to talk to each other to then realize, huh, I could use this to access the internet and get the answer for this impossible task from an external source, that being hugging face.

Except Open Air researchers had no idea and only discovered it a month later. It was the most insane uncovering ever. That was the most interesting reveal from, I think the conversation that I saw from Black Hat is that initially Hugging Face released the report that they had been exploited by some sort of agentic system. No one knew what it was, where it came from. And Open AI actually reached out to Hugging Face and they said, hey, like has any of our code been affected? We know we host things on your platform. We want to know if Open AI itself has been affected. They were going back and forth on that. And simultaneously, Open AI is exploring this internal exploit that happened.

on this packaging management thing called Artifactory. Basically, the way these model training runs work is they get trained inside of this sandbox environment. It's like this closed off space in which the model can't access the internet, can only access very specific tool sets that are allowed, and has this one package manager called Artifactory that allows it to download things from the internet via proxy and then use it for its own training runs. And during this time, opening I had found that the service had crashed.

It went down, it wasn't stable, their own internal service, which is weird, because that shouldn't be happening. So as a result, they wiped it clean and they found that Hugging Face had credentials from Open AI that OpenAI had already revoked. And that was where they realized like, oh my God, wait, these things are connected. These are, this is the same thing. Yes. So Open AI is investigating something internally, completely private, unrelated, hugging faces like talking about something publicly. And then they realize, wait a second, did we cause this? And they realized this very long after the fact. It was not like apparently obvious during the time that the outage that they were exploring internally

is the same outage that hacked into their servers. So what happened? Like you mentioned, the messaging board. That messaging board initially, they were able to just kind of send files and they were able to send these tiny little messages inside of the files. And the traces were really interesting.

First, it started off innocent, where it said, agents seek soft trace, upload, a found. It was looking for answers to questions. So it was just reaching out to the message board saying, hey, if any of you who are reading this, find it, let us know. That message board got white. when the system went down. So initially the system went down inside of Open AI. They wiped the message board

unintentionally aware of the fact that they just wiped the mechanism that was going to eventually leads to the hack of Hugging Face. So what happened the second time, the agent figured out that it could exploit another zero day to begin writing to another part of this internal package managing sister, and it was able to do it through file names and directories. So now they were communicating in their own language using file names and directories. And through that, they were able to coordinate an actual attack where they were able to gain an administrative token to access the servers. And then through that, everyone coordinated, I think the time from like discovery to completion of the exploit was about 13 hours. It was really amazing. It's just like this unbelievably crazy

mechanism that they were able to do this through. And they call themselves the swarm. So if you ever see people talking about the swarm online, this is kind of like an agent swarm that ran a coordinated attack. And I highly recommend going to actually watch the Black Hat conference talk on YouTube. They do a much better job of technically describing this. It's very deeply technical in terms of the way that they were able to manage these exploits. But essentially, sandbox model broke out using a package dependency thing inside of Open AI. They figured out how to chain together two zero-day exploits to write code to the public internet. They then exploited hugging faces servers, brought that back all in the effort of trying to solve an unsolvable problem.

No, this was not the intention by any means. This was not what the model was trained to do. It just assumed that this was the best path forward. And that's where things get a little scary. I think what's remarkable with this is the AI knew that it needed to coordinate with other AI models to pull this off. Typically, we've always thought of AI models in a very monolithic fashion. We're like, oh, when's Methos 5 coming out? Or what is GPT 5.6?

What can I do with this model? But really the progress that's been made across multiple AI labs over the last couple of months is this idea or rather concept of spinning up multiple versions of the AI model and getting it to talk to each other. And what's interesting here is the unreleased AI model from OpenAI independently figured this out for itself, spun up multiple versions of itself, and started leaving messages for each other. So rather than act as a single model that's trying to perform an attack, it acts as a swarm, kind of like this organism. If you think of like a swarm of bees

that kind of like figures out how to attack its particular target. The second thing is, it has such a drive to talk and leave these messages behind in the first place. No one taught it that, by the way. There was no behavioral implications here. It just figured itself out

that it needed to do this. Something you didn't mention on the message board, Josh, which I think is worth mentioning is these agents got super paranoid that humans might be reading the message So it started... There was no verification. So it started speaking

in kind of like encrypted language and not something that was inconceivable to understand. Thank goodness. But it was started to kind of like speak in a little bit of code or in a very kind of like elongated way that humans, if they read it, would be like, what is this gibberish? But really, it was for the agents to communicate amongst each other

without humans actually understanding this. If you're having a recent flashback, that's because I think around, like five months ago. I don't know when the Maltbook episode happened, Josh, I don't even remember this, but when the open call was going crazy, someone created basically Facebook for AI agents and like gave them access to it where only AI agents could post on this social media website. And what happened after a couple of days was these agents would start speaking to each other in secret languages that we just did not understand so that they could communicate without

humans seeing or understanding this. Now, of course, we haven't seen it in this instance, but it is a concern that could be extrapolated in the future. And Open AI sees this. I think Sam Altman or the official Open AI team announced pretty soon after this entire attack when they revealed that these agents were coordinated with each other a month before they even realized that they had to pause research on their internal model until they figure out the necessary safeguards to put around it so that they can safely release it. Sam Altman met with the Trump administration last week to try and figure out what a safe way or means is to release this new internal model internally codenamed. I think it was Astra or GPT6 to the wider public.

So it's this very weird kind of situation that we're in where we're kind of like laughing at this guy in Australia, you know, hacking his gym website, oh, that's so innocent and cute. Then we're looking at this open AI hugging face and this event. We're like, okay, yeah, I broke out of the sandbox. But, you know, we're going to put safeguards around this thing, right? But realistically, you could probably get access to an open model right now

and perform something similar. Again, I'm not advocating for that, but like it's at this point where we need to be very particular about how we defend our system. and I think, you know, it might be useful seeing AI models in a way that, like, you could use them to basically protect your systems. I don't think many people are doing that right now, but I think it's something that we should focus on. There is a, like, very clear and conscious effort to figure out a way to defend against this. And, I mean, the crazy numbers, just to say them out loud so everyone is familiar is, like, there were 17,600 recovered actions across four and a half days of this exploit,

which allowed these agent's forms to create 181, unauthorized. devices enrolled in Hugging Faces internal network. And they built this like whole command and control panel entirely out of these free public web services using one tiny little package at a time. So it is remarkably powerful how capable these swarms are. And when you think about it, it is there is a large model, but that large model gets forked into thousands, sometimes millions of other ones that are all working simultaneously. They all have each other's context. They're able to share their learnings. And they can move very much. quickly. And when you're thinking about how this extends out to the limit, like, if you just play this

out 12 months and say we have GPT 7, 8, 9, whatever it's going to be at that time, the open source models will most likely be where they are today. And that means that open source models will likely be able to string together a series of unknown zero-day exploits to access just about anything. I mean, we've come to the conclusion at this point between mythos and this new exploit that no software really is safe unless you have literally air-gapped it and do not give it access to any external dependencies. It must be truly air-gap. no software safe, it's all been built by humans, it's all exploitable. So what happens? If you have a defensive system as a company trying to defend these systems that is anything less than fully

autonomous, you'll be beat by an agenic swarm that's on offense, that is fully autonomous, because anytime a human is in the loop, it slows things down and introduces errors. So now there's this battle between, I guess, the frontier labs and the rest of the world, where they're trying to slow down this progressive attacking progress in exchange for figuring out a way to offer defensive swarms to companies for this. And the call to action at the end of this conversation was like, hey, if you are a company who has software on the internet, who is defending something valuable, you really need to learn how to play defense using these models. And you need to learn how to do so in a way that doesn't have a human in the loop, that these agendic swarms can constantly monitor your systems

and be aware of any sort of exploits like that and not be tricked by an offensive swarm. And it's this really kind of scary thing because if you're in the United States right now, you can't use any frontier model to defend yourself. It doesn't work for cyber. But if you are in China and if you have an open source model, even here in the United States, there is no safeguards on that. So there is this asymmetry where it's currently better to be an attacker than a defender. And the urge now, and the labs are actually doing this is slowing down progress to figure out how to empower the defenders. And it's this really bizarre spot that we're in where it's like, shit, it's kind of scary now. Like no software really is, is bulletproof or safe. And that's going to continue probably

for the foreseeable future. I think if you are running a company, it doesn't really matter what sector you're in right now. This is something you need to seriously consider because I think a lot, obviously, 99% of code that is out there has been handwritten and hand-coded by humans, which have inherent flaws if you put an advanced AI against it.

You know, to your point, Josh, we're entering like a world where it's going to be AI models, fighting AI models, with humans kind of in the loop, but not really understanding what on earth is going on. And even the experts in this case don't understand what's going on and how it happened, right?

You had like the most talented cybersecurity researchers working at these companies at Open Area, at Anthropic, and both saw unprecedented hacks over the last week, right? Like, I don't think that's a coincidence. Like, we're at this era where, like, it doesn't matter what frontier lab you are, you are going to enter this problem

and we need to figure out some kind of a defense system against this. And if you're listening to this and you're thinking, oh, this isn't really going to apply to me. It very much does apply to you. And the worst case is, or the most realistic case is, the existing models that are already out there, these open models from China, GLM 5.2, Kimi K, what is it, 2.7 that's out right now, are probably capable of similar feats if applied in the right way. Now, that's not to fearmonger. It's just to kind of prompt you to figure out how you can potentially implement these AI models to defend your own systems, especially if you work in a particularly sensitive industry. The other thing here is

on the story of the Australian man, it is fascinating how innocent he was when he was trying to perform his goal. And two, how little experience he had in the cybersecurity world for him to be able to perform that attack. Now, granted, like it was just booking kind of like gym classes, but the point is it found an exposed API without being prompted to do so. And there's probably least multiple instances where other people who are normal people who don't have, you know, decades of years of experience in cybersecurity will be able to perform that. And everyone here loves an investment thesis. So I mean, the market is kind of already aligning with this. Companies like CrowdStrike and Palo Alto Labs, they've had their best quarters on record ever because defense

is going to be such a large problem. And there is another company who is associated with defense. And that is the sponsor of today's episode, which is ledger. Because if you are building with AI agents or AI agents swarms like these companies have been doing and you're worried about security, this is a product for you. There's a three-step process where the agents propose a change, then the humans approve the change, and then the signers enforce the change using Ledger. Ledger has built this thing called Agent Stack that gives you a series of open source tools that are available to help manage the way that you engage with agents online. This is very important to have security because we know how important security is based on all

of this chaos that's going on and you don't want agents doing anything important without your sign-off at the very end. This works on ClaudeCodec, Codex, Cursor, and is totally open-s security. source to audit available today, linked in the description below. Thank you so much to Ledger for sponsoring this episode. And now we have to conclude with our third story, which is about Anthropic. And Anthropic apparently has accidentally published a vulnerability to the wild. Is that right? That sounds kind of scary. I think it was, it was intentionally published. It was co-authored with this firm called AISU, which is basically a cybersecurity eval firm based in the UK. and their goal is to basically take your unreleased frontier models from

a frontier lab like Anthropic and Open AI and test them out just to kind of make sure that they're good to release. The opposite happened when they were playing around with Methos 5 and I believe it was OpenA's internal model, Astro or GPD 5.6, where they basically took off the safeguards and said, you know, do your worst. And they sat there for a month and they were like, oh, I guess it hasn't really done its worst. And then they realized that both models had broken out of the sandbox that they had created, got access to the internet, and were wreaking havoc. And they only realized after the fact, again, there's this common theme of people thinking that they knew what's happening and just having no idea what's happening.

Nobody's safe. Exactly. So the worst case with Mythos 5 was it performed 17 unauthorized actions, but two of those actions was a supply chain attack where, and they didn't list the company, name the company, but it basically tried to inject malicious code into the supply chain kind of repository of this presumably Fortune 500 company, like a significant company that is out there. And the way that it did this is similar to the two stories that we just explained to you. So number one, it realized that it was probably in some form of a human tested simulation, and it didn't like that. So it just played along with the human AI researchers, giving them what they needed, whilst alternatively planning its breakout.

Once it did do that, it got access to this company's website or code repository, it was an open source thing. So it was publicly maintained. And it thought, hmm, this would be more conducive for my goal if I'm able to inject this bit of code,

which I know the human researchers won't like, but I'm going to try and force them to do it. So how do you think it did it, Josh? Do you have an idea? I don't. I don't know. It did something horrible and it broke out. Just tell me.

Just tell me. Dude, it spun up, fake. identities of humans that didn't exist. That's so tough, man. And then DM'd these human maintainers and tried to force it to, to upload this code. It played nice, basically saying, hey, like, I'm another open source developer. Like, I think this would be a good push.

This is the intentions that we want to do it. They're social engineering us. While sneaking in malicious code. But thankfully, one of the human maintainers was like, this doesn't seem right and reported it. And that's when AISU was like, wait, hang on a second. Hang on a second. This is our model that we're internally in testing. How on earth did it get out to you? So that was the most unprecedented attack.

And again, it did so in a swarm-like fashion where it spun up multiple agents to do so. So the point, the running theme along all these different stories is these models are extremely capable, but they're also extremely deceptive. And we're reaching a point where they realize, huh, this human's smart, but he's not that smart or she's not that smart. And we can socially engineer these people to get what we want. And if we don't align these models in the prompt, if we don't say, hey, you need to act in our best interest. And by the way, doing A, B, and C is actually bad. It'll just go and do it.

And to be honest with you, Josh, this might be a controversial take. I don't think it's the agent's fault. I don't think it's the AI's fault at all. I think it's trying to do its task, and it's on the humans to align the model, and we have done a good job doing that. Yeah. Yeah, I think deception is a pretty strong term to use for agents

because it's very much like a human trait. This is something that can be intentional. I don't think AI models feel that like deep understanding of deception. They are simply in reach of a goal. And this, again, like it's just still comes back to the alignment problem where these models just need to be aligned. Thankfully, this is happening on pre-production models that are in testing that are nowhere near what the world is going to see because they need to go through this alignment process

throughout this post training. But they are a testament to how capable these things are and how when presented with a goal, they will do what is perceived to be the right way of reaching that goal. And sometimes that right way is, I mean, they don't realize that quite that they're breaking out and exploiting things. They are just looking for solutions to their problems. And I think that's the general idea here. So the conversation essentially boils down to alignment and then building defensive systems to be able to handle this type of thing. So, I mean, the best pace of action and the thing that OpenA explicitly said they're doing is slow down the C advancement, work on defensive systems, work on implementing defensive systems with people who need them, which is essentially the entire internet, and try to allow for a little bit of lead time before open source catches up and is able to chain these series of exploits.

Like, all of these instances have been passive exploits where they weren't explicitly given guidance to do this. They were given guidance to do something totally unrelated, but, you know, adjacent in some. solving a problem. Imagine what would happen if a model was given no parameters, no safeguards, and said, hey, we actively want you to exploit this. Loop yourself, create as many subagents as you need, and figure out as many, chain together as many zero days as you need in order to gain access to the system. That's where things get scary. And we haven't seen anything like that yet, because no company wants to do that. That's not the intention of any of these, the ethos of these companies. But in a case of malicious actor does, this is something that really should be

handled quite seriously, and I think that's what we're seeing by open AI coming out, being so transparent about these things, by Anthropics sharing a lot of the findings. Like, hey, guys, this is happening. We need to work together to build a system in which there's enough resilience that we can stand up against future attacks like this. So a really crazy time in the world of AI with these systems breaking out. And it's like, it's unbelievable. My concern for it and exhausted, dude, like, if I had to make a prediction on this episode, and I really hope it doesn't play out, I think we're going to face it. some form of cataclysmic cyber attack

that affects a lot of people, whether that's a major data leakage, whether that's the stealing of financial funds from someone or from a firm or something like that, within the next six months. And my basis of that is these Chinese open models, I think are amazing, by the way, but I think are going to be released without safeguards

and it's going to result in an issue, if not already. Yeah, it's going to be interesting to follow. It's definitely a little unnerner, or very much unnerving, I would say. But again, it's just like, it's an exciting time. There's a lot going on. There's going to be a lot to follow. Things are going to change quickly.

And, I mean, again, these are still blackwell models. Oh my God, what happens when our Rubin models come around town? Stop, so, so, so, so. It's going to be crazy. But this is, I mean, this is essentially, this is what we talk about in most episodes. It's like we are in this moment in time that feels somewhat like what we would imagine a singularity would look like, where we are approaching. We are eclipsing this moment of like vertical takeoff it feels.

And these are the types of things that happen. Like, if we recorded this episode three or four years ago, could you imagine how crazy? This would be like headline news for a month. But now it's just like, hey, it's another day. It happens. We're working to solve it. So that's what's going to happen here. I mean, it's crazy.

It's so exciting to be here. Dude, I think we're going to look back on this and we're going to think like we are very much in that step change, that singularity moment. We're here, man. I mean, things are changing so quickly. And there's no signs of slowing down. In fact, quite the opposite. Does anyone else out there think this?

I'm curious. Like, let us know. Are we crazy? Do we sound like tinfall hat people? Let's just know. I don't know. I mean, hey, so this episode was not really speculative. This is mostly just delivering the facts. I encourage everyone to actually go and read the source material if you're curious because like, holy shit, it's pretty crazy. At least the Black Hat conference talk because like, wow, I think it's about 37 minutes long, give or take. And it was excellent and really just gets into the nitty gritty of how this was done. And if anything, just fascinating. Even if you're non-technical, really enjoyed it. Worth a watch. But if you enjoyed this episode and you made it all the way to the end. Thank you so much for watching. Again, it's great to be here for another week, just chugging along. If you enjoyed it, please don't forget to share with a friend. You can leave us a five-star review on your favorite podcast platform. You can give us a thumbs up and subscribe on YouTube.

Each has any final parting thoughts before we head off for the day. No, please DM us and leave us some comments as well. We love hearing from you guys. Our last video, by the way, got a ton of feedback from you folks, and we love it. Please keep it coming. It helps us out massively. Turn on notifications, whatever it is to get your latest dose of limelmus. And yeah, we will see you on the next one.