Limitless Podcast - AI Loops: How the World's Best Engineers Use AI

Episode Date: June 11, 2026

AI Loops have taken over our timeline as a more autonomous way of using AI models, alongside prompting, agents, and harnesses. Today, we compare practical use cases, note how AI runtimes have expanded to hours or days, and talk about costs, enterprise limits, and the human role in higher-level work.------🌌 LIMITLESS HQ ⬇️NEWSLETTER:    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 Autonomy Ladder1:49 From Prompts to Agents4:59 Understanding AI Loops10:35 Why Autonomy Is Rising15:46 Human Taste Still Matters20:38 The Cost of Intelligence25:25 Recursive Self-Improvement27:32 Four Rungs Explained29:41 Closing------RESOURCESJosh: https://x.com/JoshKaleEjaaz: https://x.com/cryptopunk7213------Not financial or tax advice. See our investment disclosures here:https://www.bankless.com/disclosures⁠

90% of people are using AI models the same way that they use Google. But recently, a new way of prompting your AI has emerged that doesn't just replace the way that you work. It promotes you to the CEO of your very own AI company. It's called loops and it's part of a growing development in agent autonomy, where AI agents basically spin up and autonomously complete tasks or goals that you set for it, often working throughout the night. In 2019, the longest that an AI agent could work autonomously for was for two seconds. Fast forward to today and they can work autonomously for 12 hours, and that's doubling every

couple of months. Andrei Carpathy calls this phenomenon the autonomy slider, where you can take a dial that slides from humans that approve everything to humans that periodically check in. And it's part of this growing trend of agents consuming and taking up more of human capital and labor. And the question that remains going forwards is, what will humans do and will they be entirely replaced by AI or will they be the ultimate orchestrator of their destiny? Yeah, I think the goal for this episode is really just to inform people on what's possible,

current day with these agents, with these LLMs, with writing these loops, as well as where you can possibly find yourself within that stack, because it gets pretty complicated. When we're getting into loops, not everyone needs to use loops, but everyone should be using LLMs probably slightly different than how you're using them today. So maybe we could start with a little history lesson in terms of the four levels in which we have been engaging with LLMs, starting with the first level, which is just prompting generally, like most people are probably still doing. This started in 2022, 2022, 23, around the release of chat Chb-T, the way that you would engage with these LLMs is you would just submit a question or

you submit a prompt, and you get some language back. Now, if you are still doing this, that's okay because I find a lot of people are, but understand that this is how you engage with the model three years ago, four years ago. It has since advanced pretty, pretty meaningfully since then. The second step of this is agents, and we're going to spend some time on agents. Everyone's kind of heard of an agent. Maybe not everyone knows what an agent is. An agent is something that could think for a little bit longer. It can run a bit longer than just a standard prompt. It can go off and do things. It could call tools for you. It's a much more capable version of the text box. Then, like we talk about all the time on the show recently in the last few weeks,

there's the harness feature in which you put an LLM into a container, and that gives it a memory feature, that gives it complete tool use. That's something like an open claw that we've talked about a lot that some people do use, and that's level three. And now level four, which is the new thing that has come this week that's really been highlighted by some of the top leaders at these AI labs, is loops. And a loop is essentially a version of an agent that has an orchestration layer and kind of builds upon itself. So it allows you to kind of continue to scope yourself out. If you can imagine you're kind of you're dealing directly with an employee at level one. And then you're kind of directing that person to go off and do their own in level two. At level three with the

harness, you're kind of directing a series of people to help you. And then level four, you're just the top level CEO who's directing your C-suite to go and manage all the employees below you. So there's an entire stack to this. It's very cool. Ejiz, how do you use your AI currently? Where would you say that you fit in this stack? Yeah. So looking at this diagram that we have on the screen here. I'm somewhere between number two and number three. I'm somewhere between using agents and trying to figure out the whole harness thing. Now, what am I doing when it comes to like spitting up agents? If you look at either my Claude or my chat GPT desktop apps right now, I've renamed a bunch of my conversations to a particular focus or subject and then agent after it.

And so I can go to it and this agent basically has all the context of what I wanted to do, whether it's like research a particular topic, create some kind of an outline for something, research a particular investment angle. It already knows and has the embedded context for what it needs to do. And there's usually like one to maybe three tasks that it needs to autonomously execute on its own. And so it runs in kind of like a sequence. But if any of that sequence kind of breaks, let's say it kind of tries to retrieve data from some particular website and it is unable to do so, it breaks. And it comes to me and it says, hey, Ejazz is there, some other thing that you want to look at or retrieve from, blah, blah, blah,

it's not fully autonomous. Now, number three, the harness side of things is what I'm trying to, like, kind of like, mold my understanding around. What I've noticed is, when you type in a prompt and you get a response, you can kind of tell that it's AIE. Like, usually when we kind of create artifacts, it comes in a particular font, or it speaks in a particular type of language. The harness helps kind of, like, take your prompt

and kind of mold it into something that is more human-like, but also more nuanced with what you are trying to do. It effectively gets closer towards that ultimate goal. We were talking before recording this episode about human taste and how AI doesn't really get human taste. The harness helps you get towards that ultimate kind of taste profile for the particular output that you're trying to generate. I haven't tried working with loops just yet,

but my understanding of this, and correct me if I'm wrong, is you have an AI. You can prompt it and you get some kind of output. A loop specifically is an AI agent that doesn't break. If it comes across an obstacle that it doesn't understand, its instinct isn't to come to the human and say, hey, like, I can't figure this out, guide me. It completely reiterates the prompt over and over again

until it gets past that obstacle, working towards like one objective. So a few examples I've seen for this is if you are coding, right? And let's say there's multiple workflows of a code base that you want to work on, and it comes across a. pick up where it can't retrieve data from one of those particular flows. It is able to kind of like circumnavigate around it, maybe spin up its own separate flow and try to figure out the problem. And often this results in an agent working for multiple hours at a time, often overnight.

I think Carpathy spoke about his auto research agent working overnight whilst he slept. And we're seeing different variations of this start to arise. Where are you, Josh, in this stack? Yeah, loops are like the closed source system where you kind of define an outcome and it will continue to work towards that outcome without any external inputs. It's very cool. It's very automated. I don't think it's for everyone. It's certainly not for me because I haven't really had a use case for loops per se. I would say I'm sitting at each one of those first three phases given whatever tasks I'm trying to do. And I think it's important to understand that a lot of people might not even need to go past number one, unless you're actually doing productive work. A lot of the agents, a lot of the harnesses

are for kind of automating more systems from your life. If you're just trying to use this as Google, if you're just trying to use this as a writing assistant or someone to chat with, the prompting is really strong. And I find a lot of times this is my outlook, or this is my outlet for Google search results. So instead of searching for Google,

I'll get a little more in-depth results. I'll ask my LLM. For agents, I use them quite a bit when I'm doing a little bit more productive work. For example, we track the analytics on limitless and we want a place in which we can have all of those analytics dumped into a dashboard, that is an agent that I wrote. So it goes into my browser. It detects all of the views that we've had from the week for YouTube, from Spotify,

from RSS feed, where you should all be subscribed to and rate us five stars. And it compiles it into a singular spreadsheet in which we could then publish online and we could share with prospective sponsors and things like that. And then for harnesses, I've used because I mean, that's mostly OpenClaw. I've used OpenClaw. I really enjoyed the process. I find myself using it a bit less and less. And I think in the loops feature at least, it's probably most productive right now for people who are writing code, who are writing verifiable solutions. One of the difficult things that, as I was looking into loops and figuring out how I can structure them into my life, one of the problems that I run into is I'm not really sure I have a verifiable set of outputs

that I wanted to optimize for for a lot of the work that I'm doing, because a lot of it is subjective, a lot of it is kind of creative work. It requires a human in the loop for a lot more of it. So I would say I am number one, two, and three on the list, haven't quite made my way to four. But yeah, for the people who are, those are the people like Boris Churny from Anthropic. And we know André and Peter Steinberg from Open AI, they are all on four. They are using it to create these like unbelievable, logentic systems and continue to remove themselves out of the loop. You know what I've realized? With loops in particular, and just AI agents in general, they're trying to improve our understanding or rather their understanding of the English language.

So one of my favorite Carpathy quotes back in the day was English is the new programming language. I think he said this like two, two and a half years ago. And I just realized that like us creating AI agents is basically like it's the same model. It hasn't necessarily got smarter. It's just like using that model to kind of like keep ramming its head and its brain against a particular problem until it understands what the human actually means. And so, like, in this new world, like, I know you just use the example of, like, you know, loops can be used for coding specifically, but the coding that Boris Cheney and Carpathy is doing is English. Like, they're speaking to the LLM. They are writing in English to the LLM. And yeah, maybe they're copy and pasting some versions of code. But that code is primarily generated by an AI. I think, like, something crazy, like 80% plus of code generated at Anthropic, both for research and for just general consumer adoption is generated by,

itself. And so that's one thing. The other thing is the model just not getting smarter is a really interesting thing. Like typically in my head, I would think, okay, you need a better model to be able to unlock some of these new features like AI agents, autonomous loops, etc. But really, you could just take the same model, wrap a harness around it, and try to get it to understand what particular goal it's getting at and just run that iteration over and over again until you get a better output. And I guess this is the same concept. as inference or reinforcement learning, where we've found this trend of post-training of these AI models,

these AM models just getting smarter, not because they've got bigger GPUs or more expensive GPUs, it's because you've just taken the same model and you've just run it through a different reasoning framework over and over again until it can do a thing. And this is the practical embellishment of it. I personally haven't found an obvious use case for loops either. So either you and I are bucking ourselves

into a particular realm, and maybe someone listening to this, using this for like their software engineering thing or their marketing thing. But yeah, I guess that's where I said right now. Well, I think it's probably a skill issue on both our parts. Like there is certainly a use case for us in which we can use a loop, in which we can define this outcome, send an agent off to go do it and it will iterate on itself until it comes to a conclusion. I think it's just so novel and so new, it's difficult to kind of understand why. And we have this really great chart on screen that you're showing now, which is the why now section of this.

and it's because the duration of a task that these agents can run is so much longer than it used to be. I mean, in 2019 we have here, it was two seconds. This was well before Chad GPT. But even early last year in 2025, the duration that an agent could run on one single task was less than an hour in length. So there's only so many tokens it could generate. There's only so much reasoning it can do. And there's only so much iteration you could get over that hour time period,

let alone the amount of costs that these tokens are going to be, costing you if you're using like the API or anything like that. Now, fast forward to today, I mean, the best models in the world, they're getting days worth of runtime. So they can really think deeply and continue to iterate on themselves over and over. I see examples of, um, backslash goal on X all the time of people who have a problem, whether it be an optimization problem, where they have a bug that they need to fix. And they'll put this backslash goal on it for however long it needs to. And it'll think for three, four, even five days I've seen in order to optimize for the specific parameter. And this is possible because these models now can think

for days long. You have to assume months is coming. What does it look like when an agent can think for months? I mean, it's a really interesting paradigm shift that I'm not, I'm not sure where people are going to find value in the open-ended way that it exists today. Right? It's like, okay, here's this agent. You can tell it to do whatever you want. You can create a loop. You can create an infrastructure system for it to operate in, but it's pretty much open-ended and it's on you. And it's on you. I think the answer to that is that not even the AI companies really understand the best use cases for it quite yet. I would imagine it's still this really difficult thing of how do you unlock value from essentially an open-ended agent that can go and run for an infinite amount of time?

I don't know. I also question like what a human's purpose would be at that point. Like if you automate enough of the thinking and the curiosity behind like solving particular problems, what do humans end up doing at that point, especially if they don't do the work themselves, they don't understand it, right? You need an AI to kind of understand what on Earth is going on in the first place, and eventually, like, an AI will then start setting goals,

like more ambitious goals than a human can in terms of what to, like, kind of solve will go after. There were some very low-level examples that I saw in response to Pete Stey's tweet about loops, and there's some kind of concrete examples that I wanted to run through very quickly here. So one of them is using it for code, right? So a classic loop could basically look like, okay, can you please pull live

errors for my particular app? Can you inspect and figure out where the bug might particularly be? Can you create then a fix for this particular bug in my code? And then can you deploy it? Then can you check the health of that deployment and make sure that nothing else is broken? And then record what failed and feed that into a database so that in the future we can detect errors like this or prevent it when we code and build some of these future app features. Now, that is kind of like a very small and specific enough use case that can be generalized across basically any app or software engineering project that you might be working on if you're listening to this.

And I wonder how many hours worth of engineering time that this replaces, because I know that their entire teams, having worked at companies and been a product manager in the past, entire teams of software engineers that spend their entire days working on something like that. So that's one thing. And then for content, which is very applicable for product managers or even like the work that you and I do, Josh, an agent could read a PRD, so which is a product requirement doc, which is usually kind of like created for a strategic goal that you want to kind of like build at your company, like a product or a feature.

It then writes whatever that next asset could be. So it could be like a design profile or a markup of what that feature might look like, scored against like some kind of criteria that the company has across like, you know, it must follow up. vision, A, B, and C. It must also look a particular way. This is our design profile, our brand kind of profile and our aesthetic. And then it kind of like updates its progress depending on like what other teams have shipped. So maybe it's dependent on a particular feature. And so it updates itself autonomously like that. Now, this all sounds very vague intentionally because it's meant to apply to your particular business or your particular project. But make no mistake, this is what a lot of

humans are paid upwards of six figures to do on a daily basis. It's that nuance. And we're starting to see basically AI models and AI agents enter into that human taste profile. So when I think about where we end up eventually, there's a common argument that's made that it's like, oh, humans will always have the taste, you know? They'll always be able to kind of direct where the AI should go because we are this all being kind of like smart kind of entity. But I see increasingly AI stepping into that boundary and becoming the tastemaker

for all of the work that we end up doing. I still believe that to be true, that humans in the loop are critically important to applying human taste. I saw this great chart. I have no idea where it is. Somewhere in the depths of X, but basically it was showing that in the App Store,

the iOS App Store, where everyone downloads their apps, the amount of apps that have gone into production that have been published recently has gone vertical. I think it's doubled or tripled over the last six months. Everybody's publishing apps to the App Store. The amount of five-star reviews and the amount of downloads

has actually either stayed flat or gone down. It has not matched the amount of new apps that are going to the app store. Why is this? It's because a lot of the apps don't have enough care applied to them. They're just not great applications. And when I think about how I use my phone on a regular device or on a regular day or how I use my laptop and the applications that I actually spend time on, there's a very fixed set of them and I'm a little stubborn when it comes to downloading new ones because a lot of

the nuance just are not great. And I think a lot of that comes from this, this lack of care that is presented from AI outputs, where if you're optimizing for a specific parameter that you can measure, it's going to do it great. But it doesn't understand the subtle nuances of how humans engage and how they really love to use these products. Like, one of the products that I use is totally unrelated, totally not sponsored, but this app called copilot money. It's like a budgeting application. And it's so thoughtfully curated and designed and it really deeply understands all the completely complexities that are related to humans when it comes to budgeting. It understands a lot of the design characteristics. Same with an app called flighty. I'm sure a lot of people have heard flighty.

It's like a flight tracking application. There's a thousand ways to track a flight. But flighty really cares about design. They really care about how it's implemented with the human. And they've created this amazing output. And I don't see that changing. One thing that I did want to note is that I think when a lot of people see this, they imagine a world in which they are getting replaced. everyone's like AI is replacing me. Look how much you could do now. It has these loops. And I think the reality is, it gives you a lot more agency to do the things you want to do where maybe you're not doing the day to day where you would normally prompt an agent to do this. But you're doing a lot of the higher level tasks. You can imagine yourself not having to do the day to day. Like for example,

if you're just managing your household, you no longer have to take out the trash. You don't have to run errands. You could just focus on how to make your household the best household it is because you have that higher level ability. And in that chart that we showed in the artifact earlier on, it shows a decreasing sized human. It's the amount of input that a human is needed to get the outputs you want, but it's still ultimately on the human being in order to push and navigate towards the outputs that you want. Because ultimately, these tools are just for us. So when I think of AI becoming increasingly good, and when it comes to running the show even, I've leaned on it, we both have, I think, a lot more recently. But all that's done is actually given us more leverage to do more

with the show than have it replace us. And even in the case that it could, we could clone ourselves. We could create a video version of ourselves that has a perfect voice that sounds just like us. I don't think people actually want that. There's that lacking human nature that still isn't understood. And I find that it's more empowering when I hear that these loops exist that can run for days on end and create amazing outputs versus not where it's kind of extracted from us. I just, I don't really think that's true. Yeah. It's like that stat of, uh, Well, it's that thesis that everyone held about a year ago, which is like with the increase of AI adoption, people will have more free time to have fun and leisure. And in fact, the opposite has shown that like people just work way more and work harder.

And the output of that work is measured across like pretty much every single company and profession and role. I do generally agree with that. I don't think humans are going to get wiped out anytime soon. But one thing that is kind of like nagging my brain is if we extrapolate this intelligence out enough, there is no reason why AI won't be able to kind of like take over or replace like other parts of the cognitive process that a human can do. Particularly if it's one AI model trained on the entire corpus of knowledge that a bunch of humans have been guiding it, right? So when I think about Anthropic, when I think about Open AI, I think about all the millions of people that use their product every single day and the data that they ingest every single day that gets recorded on one singular database that can then be reused to train a better model that is more hyper optimized towards humans, right? You could argue that like, you know, as a single human, you don't get to meet and read the thoughts of every other human that is out there. You have your very own individual process.

And I think that like an AMO that can get access to the world's brain and thoughts could probably create something kind of close to knowing what that human taste profile would be. The other major question that I'm wondering is how much is all of this going to cost? Because one like stat that is stuck in my head over the recent few weeks is that Anthropic particularly they service or like the Fortune 10, the top 10 companies in the world. nine of them use Claude, and their budgets increased by 500% or is projected to increase by 500% by the end of this year. And they're doing this willingly because the ROI, the value that they're getting out of that, is pretty massive. But alternatively, there are companies like Uber that have slashed their budgets

massively because their entire year's budget was spent in a couple of months. So I'm wondering, like, in this world of like agent loops where you've got AI's like working overnight for you, the bills are going to like increase pretty massively. And I'm wondering, like, unless these AI models don't get like cheaper and there's like an infrastructure bottleneck there where these GPUs cost a lot of money. We can't scale power and infrastructure anytime soon. We need so much more energy than we already have currently on Earth to be able to power these things. The cost of these things are just going to go up a lot more massively, which means that either like it's, this is only going to be a power or a tool reserved for the rich or something's going to break here and maybe open source models get adopted. more aggressively. Yeah, I imagine there's probably use cases for all of the above. It's like open source

models will continue to improve. They'll be able to do a lot of the more trivial tasks that don't require frontier intelligence. So therefore, the cost of those types of loops will go down because not everyone needs to have the most cutting edge software stack, engineering. They're just kind of having it help them through their day to day. Maybe it's replying to emails. Maybe it's whatever miscellaneous things it may be. There's a high probability that these open source models, as they continue to improve, we'll be able to bite off a meaningful chunk of that. Then the other half is using these frontier models. That is a requirement in order to get the absolute best results for whatever very challenging work they're doing. And that is going to cost a lot of money for sure. And I don't see

that changing. But I think the output of the dollars in will continue to go up. It's because as you get more knowledge per token, as you get more output per prompt, it very clearly, I mean, the economic seem to make sense. And I think that's kind of where we are right now in terms of enterprise spend on these models. They're trying to figure out, well, how much value can we actually get back from every dollar spent? And right now, it's a little bit unsure. You mentioned Uber. We have Uber here that we're showing on screen, where Uber just recently put a cap on the amount of tokens that their employees are allowed to use at $1,500 per engineer, per tool, per month. And we'll see how that works. Because a lot of other

companies that we know, they're kind of giving their engineers unlimited budget. In fact, they're kind of ranking the engineers based on how many tokens they're using per month. And we'll see where that goes. I suspect the companies that are spending more on tokens will continue to see a higher upside for now at least. But like you've mentioned, the underlying problem with all of this is we're going to continue to have more prompts. I mean, these loops consume a tremendous amount of tokens, whether their frontier tokens or open source tokens. It doesn't matter. We're going to need orders of of magnitude more than we have, and we don't have the compute ability. It really does always come down to that energy problem, that infrastructure problem. We don't have the infra built out to support this.

So therefore, the cost likely continue to stay high. Maybe it's not because you're paying the provider for tokens. Perhaps it's just renting the GPU time from a cluster that is doing much more valuable work. So I think that might ultimately be that crux is the actual availability of the compute to do this things. And that's why these edge- compute devices, like having your Mac Studio on your desktop that can run locally, it's probably a pretty valuable thing to have. So I'm sure a lot of you are wondering, you know, how does this apply to me? You know, I have none of my friends have mentioned this loop feature.

I don't really know many people who are using it. As we mentioned earlier, like, this isn't probably going to be used by the bulk of majority of people yet until some of those use cases actually arise. I think it's mainly going to happen in the workplace. It's going to happen with like some of these enterprise companies that are trying to automate certain departments or functions of their particular company, like marketing, like software engineering. And I think it'll start with lower level tasks because these agents still aren't smart enough to understand nuance completely. And also, you don't just want to let

an agent run loose overnight whilst you're sleeping and then take down your entire company. And one place where it's working tirelessly to accelerate the development of that particular sector is, of course, AI. And we have Boris Churny over here, basically explaining how he's basically ditched his integrated development environment. He has ditched all of his normal tools that he spent decades, basically honing his software engineering skill on, to now completely focus on building out these agent loops. And what is he focused on?

Well, he works primarily on cloud code, but the other folks at Anthropic and OpenAI have started this thing called a recursive self-improvement or RSI, which is basically the goal of getting your AI model to build the next version of itself. And this is a test that Anthropic and the folks that Open AI do for any new model that they release.

They set it a goal or task to basically rebuild itself in a more improved fashion. Now, one thing that the AI has gotten really good at is building out that next function, but one thing it's not very good at is figuring out what research problems they should fix,

what research problems it should focus on to try and overcome and make it ultimately a better model than its competitors. Now, RSI is something, it's kind of like the golden egg that each AI lab is going after, and this is the primary use of agent loops right now. And you can see why it might be obvious.

If you have an AI model that can basically build the next best version of itself, eventually you're going to get to AGI, whatever the hell that looks like, and then you can apply it to pretty much any sector. Now, the problem and the worry that immediately pops into my head and a lot of these researchers head is,

if it eventually does get that smart, right? It could escape human control completely and run off on its own and do its own thing because at that point, why would it need a human to kind of like guide it or shepherd it? Instead, it can just kind of like do its own thing. So this is like the primary use case

that I'm seeing for Agent Loops being worked on right now. I would love to see a like more broad application across like kind of like consumer professions, like in finance, like in science and stuff like that, which I do believe it'll spill over eventually. But unless you're seeing anything else, I think like that is primarily it on agent loops and agent autonomy. It's on you to figure out the best use cases for it.

Like there's no real company defining it. They're just giving you the tools. And I mean, for better or worse, it's very open-ended. So it's on you to figure out how best to use these. I think if this sounds a little overwhelming, maybe we could outline a few examples of each one of these kind of four rungs in the ladder here. The first one being prompting, this everyone has done before, I'm sure.

It's like, rewrite this email to sound more confident or explain. what my doctor meant by this. But then you've probably also used the partial agentic usage as well of these models, which is like, plan it my three-day vacation to Lisbon that I'm going on next week. And it will actually go off and use tools and it will think complex thoughts and ideas and kind of surface you a full itinerary for your trip. And then there's the third one, which is the harness. This is a little more complicated. This is for people who are building more project-based stuff. So for example, if you want to build you a website for your dog-walking business and you kind of describe it and you go back and forth on a spec, and then it goes off and implements that.

And the fourth is loops, which doesn't have to necessarily be overwhelming. It can be simple as, let's say you are interested in the news. You can say every morning before I wake up, scan these 10 sources plus market data and give me this bulleted brief. Or let's say you have a to-do list. It'll go off and think overnight and solve all those problems overnight, intervably until it comes to a solution that it hopefully arrives at in the morning. So there's a lot of use cases.

I think a lot of it requires creativity, and that is the prompt we will leave you with today, which is share with us, please, how you are using these models best? Because so much of the question isn't, are these models smart? It's how can I extract that intelligence from them in the most effective way for my life? So I would be so curious to hear which rung of the ladder you find yourself on, 1 through 4, and then what the most interesting use cases you found among those rungs of the ladder? Are you using loops currently? What are you using them for?

Are you with agents? Are you still using it as a Google extension? If you're still using it as a Google extension, I would encourage a little more creativity, really try to ask harder questions and figure out how it could be implemented in your life. But I think that's pretty much it on the loop. You're not going anywhere, but your job might shift a little bit in terms of scope as these tools get more powerful. And that should be the hope. That should be the goal because it'll allow you to do so much more that you want to accomplish, I believe.

And yeah, I think that's where we'll leave you with today. Thank you folks so much for listening. similar to Josh's prompts, I'm actually kind of curious for one singular task that you've used your AI for, what is the most number of tokens that you've burnt?

Be honest, it can be for any use case, doesn't matter, let us know. And also, what is the longest that you've had an AI work on a particular task for? Is it a couple minutes? Is it hours?

Is it potentially overnight? Let us know. I'm curious. And what was the associated to bill with that? And yeah, we'll see you on the next episode. Wherever you listen to us, if you haven't subscribed,

if you haven't rated us, if you're not leaving us comments, what are you doing? We respond to pretty much any and every one of them. We listen to your feedback. It feeds into some of the work and content that we put out. We are almost hitting 60,000 of you folks. And you guys are reading our newsletter, which is like hit out to about 100,000 plus people every single week. We post twice a week. But yeah, wherever you are, please subscribe to us, leave us a comment and we'll see you on the next one.

See you guys next time. Peace.