Ep 390: How to use Claude’s AI ‘Computer use’ for everyday people

Resources:

Join the discussion: Ask Jordan questions on Claude AI


Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup

Connect with Jordan Wilson: LinkedIn Profile

Try Our Free AI Prompting Course: Register for our free Prime, Prompt, and Polish AI Course! 

AI Tools for Everyday Tasks

With Claude, interacting with AI becomes an experience rather than a task. Its functionalities range from gathering company information to drafting Word documents. Although currently error-prone, the AI tool is showing promise in navigating websites and accurately extracting necessary data.

Unfortunately, it tends to miscue its Firefox queries, mistakenly routing them to spreadsheet inputs. These errors are part of the everyday challenge with cutting-edge technology. However, the directional guide feature can mitigate these issues, serving as a helpful feature to maintain process flow during task execution.

Interfacing with AI: Docker and API Keys

Docker, a popular platform used to automate applications' deployment, lends a helping hand in effectively interacting with Claude. By following a brisk setup involving pasting an API key into a Docker terminal command, users can comfortably navigate this program. It is crucial to ensure that API keys are kept confidential, as unauthorized usage can lead to unexpected billing issues.

Notably, this process offers insights into the world of computer vision and autonomous operation. Through a virtual desktop and chat interface, Claude can conduct tasks like online searches, screenshot generation, error handling, and more—making AI an accessible and practical tool for everyone.

Evolving AI Tools and Future Expectations

The technology landscape is constantly shifting, and new updates are continuously being rolled out to improve AI tools. Claude's 3.5 SONNET Update and the expected 3.5 Haiku are prime examples of this evolution at work.

That said, there are still limitations. Tools, like those from Anthropic, have tight restrictions that may prove challenging for users. A clear example is Anthropic's computer use tool, accessed through its API or platforms like Amazon Bedrock and Google Cloud's Vertex AI. While it is experimental and limited, it is publicly available—a testament to the ever-growing AI ecosystem.

Similar developments are happening across multiple tech giants, with Google's Project Jarvis and Microsoft's Copilot Studio’s Agentic AI under development and Salesforce's Agent Force expected to penetrate various firms by 2025.

Learning the Language of AI

Understanding the language of technology is vital. APIs, or Application Programming Interfaces, enable front-end user interaction and back-end development—an essential component in the AI context.

Ultimately, engaging with AI, no matter how imperfect, presents infinite growth and learning opportunities. With tools like Claude, everyday individuals can harness the power of AI to bring efficiency and innovation to their lives. Lastly, keeping oneself updated with developments in the AI world and contributing feedback is essential to driving the evolution of such technologies.

Topics Covered in This Episode

1. Overview of Anthropic Claude
2. How to Use Claude Computer Use
3. Critiques of Anthropic's Tools
4. Future of AI Agents

Podcast Transcript

Jordan Wilson [00:00:15]:
Whether you know it or not, you're going to be using AI agents in your business in 2025. Let me repeat that. In 2025, you will be using AI agents at your company, especially if you live in the US, whether you know it or not. Alright. So you might as well get ahead, understand what's going on in the space, and stick around for the next 20 ish minutes, and you're gonna see live. And, hey, if you're following along on the livestream, you can even, go ahead and use an AI agent. So we're gonna be talking today about how Claude's agent works. It's computer use.

Jordan Wilson [00:00:58]:
And like I said, give me about 20 minutes, and we'll go ahead and do it together live. Alright. I'm excited for this. If you're new here, thanks for tuning in. My name is Jordan Wilson, and welcome to Everyday AI. We're a daily livestream podcast and free daily newsletter helping everyday people leverage generative AI and how you can actually use it to grow your company and your career. So maybe you're listening on the podcast. Thank you for tuning in.

Jordan Wilson [00:01:22]:
Please, if you haven't already, go to your everydayai.com and sign up for the free daily newsletter. For our livestream audience, thank you for tuning in as well. Technically, debuting this live, but it is prerecorded. So if you want the daily AI news, don't worry. It's gonna be in the newsletter today. Also, if you are listening on the podcast, this is gonna be a little bit of a more visual episode. So you might wanna listen to this. If you normally listen in your car, at the gym, walking your dog, whatever it is, thank you, number 1.

Jordan Wilson [00:01:52]:
But this might be one where, hey. Go check out today's newsletter and go watch this if you do want to kind of learn along, because I'm gonna break down how to use this new computer use tool from Anthropic Claude. I know some people, you know, were asking for this when we did, cover this news last week. So, hey, if you ask for it, we're gonna do it. Alright. So without further ado, let's get straight into it. So, last week, Anthropic Cloud announced a couple of things. They announced a 3.5 SONNET update.

Jordan Wilson [00:02:24]:
So it's kinda weird. They already had a 3.5 SONNET. I kind of just call it 3.6 or, you know, maybe we refer to the old SONNET as 3.4. But anyways, they released, an update to Claude 3.5 SONNET, which is out. And then, they announced 3.5 haiku, which should be out any day. No word yet on what their big model Opus, which is still on version 3, if that's gonna get any love or any updates, we will see. But probably from Anthropic's announcement, what got everyone talking, including us here on the Everyday AI Show, was its new computer use tool. Alright.

Jordan Wilson [00:03:04]:
And, if you do want more on this, this is today's is gonna be a little bit more of a of a demo. Right? So if you want more on what was announced and what our takes on it, what our takes on it were, make sure to go check out episode 386. It'll be in your show notes as well. Alright. So here's what, this new, computer use is. Well, according to Anthropic, they said it is a new capability in public beta. So it is, available now. It's called computer use, and you are going to use, your API key.

Jordan Wilson [00:03:36]:
Don't worry. You don't need to be a developer. Even though it says developers can direct Claude to use computers the way people do, anyone can. Right? Everyday AI, it's for everyday nontechnical people. So I'm gonna give you the walk through. Don't worry. One thing that Anthropic and I couldn't agree more. They're saying it is still experimental, at times cumbersome, and error prone.

Jordan Wilson [00:03:58]:
The thing that is most cumbersome is you can barely use it. Yes. If anyone at Anthropic is listening, and

Jordan Wilson [00:04:06]:
I always love it.

Jordan Wilson [00:04:07]:
You know, I had had some people from OpenAI reach out to me recently, said everyone's everyone here has listened to the show. Thanks. But, hey, Anthropic, you should listen to, because, you know, one thing I always do here is I I literally have trained thousands of business leaders in the US on different AI tools, and cloud is very difficult. It's it's, the the limits, the usage rates, even in the API are so limited unless you are on a higher tier. So Anthropic really needs to get their program together, if I'm being honest. Otherwise, they are gonna get smoked by everyone else because it is so hard to even use their tool and experiment and to see if it's going to work for your business. Alright. Anyways, let's just jump, a little bit into the landscape.

Jordan Wilson [00:04:48]:
So not only do we have the computer use tool from Anthropic, but we just got news that Google is reportedly developing its own version of this, of its, computer using agent, called project Jarvis. We'll see if that name actually makes, actually makes it, to production, mainly because some other company had tried to use Jarvis in an AI product before. We had been we've actually been using it now for, I don't know, three and a half, four years since it came out, and they had to change their name to Jasper. So we'll see if Google can actually, you know, come out with this project Jarvis, but they're not the only ones with a computer use tool. It's been rumored now for probably 10 months that OpenAI, is working on agents. We saw Microsoft should be out literally any day, with its, with its new copilot studio, Agentic AI, as well as Salesforce with its agent force. So that's why I said at the beginning of the show, you're gonna be using AI agents whether you've whether you want to or not. Like I said, it's coming to Microsoft Windows, alright, inside Copilot Studio.

Jordan Wilson [00:05:57]:
It's coming if if you are a company that uses Salesforce, which is the most dominant CRM player around, you're probably gonna be using Agent Force in 2025. Alright? So, currently, it's available. So one thing about Anthropic, even though I don't think it's that good, computer I don't think computer use is that good, it is extremely limited. It is hard to try out, but, hey, they shipped it. So, hats off to Anthropic, they shipped. Right? They didn't launch a blog post and wait list, which sometimes Google and OpenAI kind of do. Microsoft a little bit as well. So they shipped it.

Jordan Wilson [00:06:33]:
And maybe too early, but, I I I guess it's better than not shipping. But right now, you can only use it, via an API. So if you're using Anthropics API or you can access it inside of Amazon Bedrock or Google Cloud's Vertex AI platform. So, yeah, this isn't something where you log on to Claude AI, or download a desktop, application from Claude. And, it's not how it works. So we're gonna do it live, and you have to actually download a separate program. You know, if you actually wanna, take the simplest route, and this is what Anthropic recommends. Alright.

Jordan Wilson [00:07:09]:
A couple of things. Let's first go over some terminology because when I'm doing this live, I'm probably not going to be, giving you definition. So I said, alright. Especially if you're listening on the podcast, let me break all of these definitions down that I'm

Jordan Wilson [00:07:25]:
going to be talking about. So first of all, anthropics API. Alright? So

Jordan Wilson [00:07:32]:
if you don't know in API, it's an application programming interface. Right? But in all of the large language models, you know, you essentially have the option to either use it on the front end. Right? So you can go to chatGPT.comorclaud.aiandchatwiththechatbot. Right? Or you can use it on the back end. And this is generally what developers will do. Alright? When you know, if you're fine tuning a model, bringing, you know, your company's data in with RAG, if if you're building third party applications, you know, for the most part, you're using either OpenAI's API, Claude's API, Google Gemini's API, etcetera. So, all these programs, you haven't you can go get an API key and build an application. So that's kinda what we're gonna be doing here.

Jordan Wilson [00:08:15]:
So the only thing you need to know about this is you can still use Claude's free plan. So even if you're not on their paid, I I forget if it's 20 or $30. I think it's $20 a month. So even if you're not on their paid plan, you can still use their API, but it is a pay as you go. So you will pay for actual usage. Alright. So, the other thing when we're talking about API keys, you know, I'm gonna show you mine on the screen, and then when I'm done, I'm going to delete it. Right? So you always wanna keep your API key kind of secret because if anyone gets it, they can essentially use it in their programs and run up, you know, run up a bill on you until you notice it.

Jordan Wilson [00:08:55]:
Alright. So, it's it's when you are doing this, you do need to have a credit card inside of the Claude API, and you need to, preload some money in there if you want to do this and follow along. Don't worry. I'm probably gonna blab on for another 3 minutes before we do this live. So if you want to, go ahead, do it now, and and you can log in to the back end, of the Claude system, which I'm gonna I'm gonna go ahead and, announce that. It's council.anthropic.com. Alright. And here's here's the bad part.

Jordan Wilson [00:09:28]:
It is so limited. Alright. So, I would say most people, you're gonna be on tier 1. So essentially, Claude gives you a tier depending on how much you use their product. And I'd say even people that I know in the AI space, even they're all on, tier 1. So unless your company has already been using, Infropix API for a very long time, or if you're an individual, you're probably gonna have to start on tier 1, which is extremely limited. You can barely do anything in this computer use, unless you're on a higher tier. Alright.

Jordan Wilson [00:10:01]:
So that's terminology number 1 is using your anthropic API key. Terminology number 2, GitHub and a GitHub repo. Alright. So GitHub is essentially a website where developers, but even everyday people, can go ahead and store and share the code that they write and projects that they work on. Then other people can go kind of download them and fork them or edit and add to them. So a GitHub repository or a repo is kinda like a folder with a bunch of code in it, and it holds all of the files and information related to a specific project. And the reason why this is important, and we're gonna be doing this all live as well, anthropic released computer use in a GitHub repo. So everyone can go on there and they can kind of build off it, but that's that's how you use it.

Jordan Wilson [00:10:46]:
So like I said, you don't access this via a, a website. Right? You don't go to claw.ai. You have to actually grab the information from Anthropic's GitHub repo. Alright. So again, think of that as a place where, if you don't already know where everyone kind of stores their code and you can go download it. People can modify it. Not there, but they can create versions of it. Right? So think of it like templates.

Jordan Wilson [00:11:11]:
Right? So, people put their code up there. You can go look at the code, you know, improve it. You know, if you don't know GitHub, it's

Jordan Wilson [00:11:18]:
a great place. And then last but not least, Docker.

Jordan Wilson [00:11:22]:
Alright. So Docker is a program. It's one of the ways that Anthropic recommends that you use the computer use program. So Docker is this is essentially a tool that helps developers package their applications and everything they need to run them into a small portable container that can work anywhere. So, the kind of the way I like to describe a Docker is it's a closed environment where you can essentially run programs. So it's kind of similar to terminal. Right? If you use a terminal on Mac, it kind of has its own terminal. It just helps you run everything in a contained way, and it can work from anywhere that you download it.

Jordan Wilson [00:12:05]:
Alright. So enough chitchat y'all. Let's do this live. I said we would try to do this in minutes. Let's see if that actually works. Alright. So this is going to, this is gonna be a fun one here, y'all. So let's go ahead.

Jordan Wilson [00:12:19]:
I'm gonna share my screen. Let's see if we

Jordan Wilson [00:12:22]:
can get this, let's see if we

Jordan Wilson [00:12:23]:
can get this

Jordan Wilson [00:12:24]:
going. Alright. So now if you're listening on the podcast, I'm gonna try to do my best to walk you through exactly, what I just told you. So first, we are now on Anthropic's GitHub repo. Okay? So, essentially, like I said, there's a lot of different files in here, and there's different there's different ways, there's different ways as well, that you can use this. Okay? So, the way that we are going to do it is if you scroll down here, it's going to give you some directions, and it essentially gives you this little piece of code. Okay. So I'm going to copy and paste this code.

Jordan Wilson [00:13:04]:
I'm actually putting it up in my browser, so it's all gonna be flat, and then I'm going to, oh, let me share that tab. There we go. Alright. So now I'm I have it pasted in here. Okay? I have a Word doc. So all I did is I went on, Anthropic's GitHub repo. I went down here. It gives you the code essentially that you need to run.

Jordan Wilson [00:13:25]:
Again, I'm simplifying this. And, so what we're gonna do next is there is a placeholder where you're going to need to enter your own API key. Okay? And then we're gonna combine those two things and then we're going to put them in Docker and run it. Okay? So, let's look at Docker here quick. You need to, go to docker.com and you need to download Docker for your desktop. So I am on, I've already downloaded this, but you're gonna go ahead and download this whether you're on, Mac Intel or a Mac Apple. So I'm on a Mac, Apple chip. I think my computer has like a m 1 or m 2.

Jordan Wilson [00:14:06]:
So you just actually need to download it for your operating system as well as, what chip architecture you run on. Right? So, whether you're on, Intel or, an m chip, for Mac, and then on Windows, whether you're on an AMD or an ARM chip, and then, Linux. Alright. So you're gonna download Docker and then install it. Alright. I already did that step. I think everyone out there, if you're listening to this podcast, you've gone to a website before. You've downloaded a program and installed it.

Jordan Wilson [00:14:35]:
So very simple. Alright. Step 1, where we copied and, pasted that code from Anthropic. Alright. Step 2 is we've downloaded the Docker Desktop, and installed it and opened it as well. Alright. So now, let's see. I'm gonna have to share my whole screen here in a second.

Jordan Wilson [00:14:55]:
So, I'm also on my computer. FYI, you won't see this, live stream audience, but I've opened Docker. And then when we're ready, when we're ready to get Docker going, I will share my whole screen. So we'll be jumping around

Jordan Wilson [00:15:10]:
a lot. Alright. And

Jordan Wilson [00:15:12]:
then our last step is we need to create well, not our last step, but our last ingredient, so to speak, is we need to get, that API key. Okay. So here's the thing, when I was talking about limits. So you have different limits. So it says that you have a 50 request per minute limit if

Jordan Wilson [00:15:32]:
you are on the tier one plan. I'll let you guys be the judge.

Jordan Wilson [00:15:36]:
I would say that's not true. Alright? Because it's it's very hard to run any commands even though I am on a tier one plan, and it says, for this new Claude Sonnet 3.5, the 10/22 version. Yes. I wish they just called it 3.6. So we didn't have to call it Claude 3.5 22. But it does say you get a 50 request per minute. I don't think that's actually the case. Or who knows? Maybe it just takes so many tokens, because you're technically using computer vision every step of the way.

Jordan Wilson [00:16:04]:
So that adds that is actually probably how many requests. But to do the simplest thing, you'll see we're gonna time out a lot. Alright. So, you can check your limits, but, you can go into API keys, and we're gonna create an API key. Okay. So like I

Jordan Wilson [00:16:20]:
said, after you use this API key,

Jordan Wilson [00:16:25]:
or you're not gonna use mine. Alright? So I'm gonna go in, I'm gonna copy and paste, my API key, and I'm gonna be deleting it right after this, so, no one can run up my bill. Right? So first, you need to give it a name. So I'm gonna call it, I'm just gonna call it test dash computer dash use. Okay. Then you need to select a workspace. I'm gonna put it in my default workspace, and I'm gonna click add. Alright.

Jordan Wilson [00:16:50]:
And then from there, I have a API key. Alright. So I'm gonna go ahead and copy that API key, and then I am going back to this document. Okay. So now here's what I'm doing. I know there's probably, on my screen a lot of things going on. I always like to do this, just to make it a little simpler. Alright.

Jordan Wilson [00:17:08]:
So in my original API key, there is essentially a placeholder, okay, where it says API key equals, and then it says, you know, dollar sign anthropic_api underscore key. Okay? So I'm copying now my API key that I just used, and I am going to place my cursor, and I'm gonna start with the dollar sign. So it says API key equals dollar sign, and I'm going to highlight through key. Alright. Just the y in key, not an extra space or else you're gonna run into some issues. And then all I'm gonna do while that's highlighted is paste my key in. Alright. And then from there, it should hopefully be pretty simple.

Jordan Wilson [00:17:50]:
Right? I did one test on this before. Sometimes it's a little buggy. So now all I'm gonna do is I'm going to copy this. Alright. So essentially now, I have this command that I'm going to put into Docker that I got from, Anthropic's quick start guide on their GitHub repo. I got my API key. I copy and pasted it, and then I pasted my API key into this Docker command that we're gonna then go ahead and put into the Docker program. Alright.

Jordan Wilson [00:18:21]:
So I hope I hope that makes sense. So now now we're gonna get a little wild here because now I'm gonna share my whole screen, and hopefully this won't be, hopefully this won't be too wild. Alright. Let's go ahead and share my whole entire screen here. Alright. Let me close let me close some other programs so we're not, so we're not too distracted here. Alright. We should be good.

Jordan Wilson [00:18:47]:
I'm gonna share my whole screen and let's get into it. Alright. So this is the Docker Desktop program. So like I said, you download this, you install it, you launch it. Alright. Now here's it's it's kind of hidden. Remember how I said this is kind of like the terminal program? So you're gonna wanna click the terminal at the bottom, and it says a terminal directly within Docker Desktop. Alright.

Jordan Wilson [00:19:14]:
So, from there, you might the first time you run it, when you click that little terminal, you will probably get a button the first time. I believe it says, like, enable terminal or something like that. So I can't rep re replicate that, but there will be one little button there that essentially says, you know, enable terminal. Alright. So now, I have essentially what looks like a normal terminal. Alright. I'm gonna zoom this up a little bit, so hopefully everyone can see it. Alright.

Jordan Wilson [00:19:39]:
So I have a a normal terminal here. Now all I do, I don't have to do anything else. Remember, I copied that combination, so of the, from the GitHub repo, and the API key where I inserted, mine, and I'm gonna paste it, and I'm gonna hit enter. It should take just a minute just a minute to run. Alright. And so you'll see it it says starting, so it's essentially, at the bottom of my screen, I can see it's kind of running through. It I might actually run into an error here. Again, it's very, very buggy.

Jordan Wilson [00:20:17]:
So okay. So it looks like it looks like it worked. So, yeah, sometimes if it doesn't work, just try it again. But what you're looking for, you might run this and be like, okay. Well, what happened? Okay. Well, there's just a little link at the bottom. It essentially says open, and then it gives you a local host. Alright? And all that is, think of it as this way.

Jordan Wilson [00:20:36]:
It is a essentially a local version of a website that is technically running through something else. Alright? So in this case, we are technically running a local website through all this code that we just put into Docker. Alright? So now I'm gonna click this. It's probably gonna open in a separate window, and I'm gonna have to drag it onto my screen. Don't worry. Alright. So let me go ahead

Jordan Wilson [00:20:56]:
and click that. It did open into a different window. Now I'm dragging it over. Alright. There we go.

Jordan Wilson [00:21:04]:
So it is working. Alright. Now let me explain what we actually have here. So we are on this local host, and it says Claude use, computer use demo. It says security alert, never provide access to sensitive accounts or data as malicious web content can hijack Claude's behavior. Alright. And then you can do chat or you can look at the exchange logs. All we're gonna do is we're just going to chat.

Jordan Wilson [00:21:31]:
Alright. I'm gonna move this a little bit, so we're not blocking the screen, and so hopefully we can see as much as possible. Alright. So essentially, on the left side, we are gonna be talking to this Claude computer use, and then on the right side, there is a virtual desktop. Alright. This looks straight out of 1990, maybe 1995 if we're being nice. So, for a podcast audience, it's a split screen. I'm I'm gonna be able to talk to a version of Claude in this computer use demo.

Jordan Wilson [00:22:00]:
And then on the right side, if everything works, it is going to execute things in a virtual environment. Alright. So here's what we're gonna do. I'm gonna go ahead and paste this in. So here's what I'm saying. I'm saying, please find the largest American companies by market capitalization. Save the top 3 in a spreadsheet. Include their rank name symbol.

Jordan Wilson [00:22:22]:
I should probably spell symbol correctly even though Claude will probably understand it. Right? Because, again, I am still talking to Claude, the large language model that's very smart and can understand human lang human language. Right? And that's that's the key here y'all. You are still getting the power of Claude, but you are just adding to it the ability to use a computer. Right? So it's using a digital computer. Alright. So I'm saying, please find the largest American companies by market capitalization. Save the top 3 in a spreadsheet.

Jordan Wilson [00:22:52]:
Include their rank, name, symbol, market cap, and then their CEO. So this part might be a little tricky, so we'll see how it handles it. So, and then I'm saying and add that in there as well. I should probably say add that in the spreadsheet as well. Alright. So I'm gonna say add that in the spreadsheet as well. Alright. So on the virtual desktop, there is absolutely nothing.

Jordan Wilson [00:23:17]:
Alright. So I'm gonna put my hands in the air once I do this because, you know, I'm sure our livestream audience or maybe if you're watching this later on YouTube, you might not believe it or understand it. Alright. So, I'm gonna click go, and then on the left side, how it actually works is it takes a bunch of screenshots. It uses computer vision, and then it maps out what it wants to do on this virtual desktop. Alright. So I'm gonna go ahead and click enter. We're probably gonna get a bunch of errors, but here we go.

Jordan Wilson [00:23:49]:
Alright. So for our podcast audience, it's saying, okay. I'm going to click on Firefox and search for this information. So it brought up Firefox. And now let's see. So on the left side, I'm seeing each and every time it's screenshotting something. So now it's searching and it says largest companies by market cap 2024. So it brought up a Google search result.

Jordan Wilson [00:24:11]:
So we're gonna see if it's gonna try to grab this information because it kinda brought in an AI overview. So I don't know if it's gonna go in there or go to a website. So it looks like it's not even gonna go into a website. Doesn't look like it. Alright. So, let's see. It's still running. Alright.

Jordan Wilson [00:24:31]:
So interesting. So now I got a new error that I haven't seen before. It said warning. Alright. So now I'm just scrolling up to see, but it's still doing everything by itself. It said warning failed to launch Java LDX. Java may not function correctly. Alright.

Jordan Wilson [00:24:46]:
So but it looks like if you see at the top here, it's still running, and it's doing some things to counteract this. Alright. So I can still move my mouse, but I'm not taking over anything on the screen. So it's already typing.

Jordan Wilson [00:24:58]:
Right? So it says rank, company name, symbol, market cap,

Jordan Wilson [00:25:05]:
CEO. Okay. So, again, podcast audience, my hands are my hands are folded on screen, and now Claude is doing all of these things in the computer use tool. Alright. So I'm gonna scroll down here because I'm guessing we're gonna run into an error pretty quickly. Alright. So, again, when it Googled these things, it didn't even click, into a website. It grabbed information, from the AI overview.

Jordan Wilson [00:25:33]:
Right? So, you know, sometimes you put in some information, and you don't even have to go to a website. So Claude didn't even need to click on the website, visit it. It essentially retained this information. I'm actually gonna scroll up here. I wanna see how it recorded it. Okay. So it looks like right here, it did just scrape all of this information. I'm not sure if that's where it was.

Jordan Wilson [00:25:59]:
Yeah. So it looks like it did not even go into the information, and it grabbed the top 3 US companies by market cap. Alright. And you'll see I'm pretty sure let's see. Okay. I didn't run into an error yet. It's still just a little slow. I would have assumed that I would have already hit a, a token limit here because let's see how many screenshots it did.

Jordan Wilson [00:26:21]:
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13. Yeah. So it already did way more screenshots than it did previously in my other testing. And it looks like it just stopped for whatever reason. Again, Anthropic said this

Jordan Wilson [00:26:37]:
is very buggy. As you can

Jordan Wilson [00:26:38]:
see, it's buggy. Alright. So now it's going again. So let's see. It said, alright. Here's why. Because that original information did not have the CEO. All it had was the company name, the symbol, their rank, and their market cap.

Jordan Wilson [00:26:52]:
Alright. So, this is funny. It it kinda failed here. So it said, let me search for Apple's CEO in Firefox. Alright. It didn't bring it up on my screen. Alright. And then it it said let's see.

Jordan Wilson [00:27:07]:
It looks like it just put in the CEO column on the spreadsheet, and it's using LibreOffice, which is essentially an open source free version of Microsoft Office. So it's it's it got some things wrong here. It didn't didn't do it very well, because now it's saying, again, let me switch to Firefox and search for the current CEOs of these companies. So it didn't it didn't do it very well here. I'm scrolling down here. It looks like there is

Jordan Wilson [00:27:36]:
an error. Alright. So now I finally hit, the rate limit.

Jordan Wilson [00:27:44]:
So let's look at the let's look at the the, the spreadsheet here. So there is something when you run this. There's a toggle screen button in the upper right hand corner. So it's a toggle screen control off. So I can click it and now it is on. So now I can actually go in to the actual spreadsheet. Right? So I'm clicking on an empty cell and you'll see I can type in here if I want. I just type the word type.

Jordan Wilson [00:28:09]:
So, it looks like this failed because instead of actually finding this information, it just typed in who is Apple CEO 2024. Instead of typing that in, to Firefox, it actually just typed that into the spreadsheet. So it ran into an error there and did not complete this. Alright. And then you'll see it says essentially retry after a minute and 27 seconds. Alright. So in theory, I'm talking right now because I'm biding my time. Sometimes you don't even have to wait that long.

Jordan Wilson [00:28:44]:
I'm gonna try it again, and I'm just gonna say I'm gonna, toggle the screen control off. Actually, I need to toggle it back on and get off that, get off that that cell I was on, and I'm gonna say, please con I'm just gonna say, please continue. So I'm not gonna guide it. Please continue. Alright. We'll give it a second. A lot of times it takes a second for your, for your message to show up. So now it's saying running agent.

Jordan Wilson [00:29:14]:
Alright. So let's see if it can pick up and, see where it went wrong. Those little sounds you may not hear, that happens, essentially each message. I might just have

Jordan Wilson [00:29:25]:
to mute this so it doesn't bug me. There we go. Alright. So

Jordan Wilson [00:29:31]:
not not doing not doing the best here. So, again, we're just running into some repeated errors. It does it looks like for whatever reason, it's actually struggling, to go back to, Firefox. Right? So it it looks like it's struggling to toggle, between the 2. At least I'm not seeing anything on the left hand side. It's showing me all of these, all of these screenshots that it's taking, and it's really just every time it updates something in the in the spreadsheet, it's just taking

Jordan Wilson [00:30:05]:
a photo. Right? So didn't do

Jordan Wilson [00:30:08]:
a good job here. I'm gonna go ahead and say it failed this failed this task. Alright. So I'm gonna toggle screen control on. I'm gonna go ahead and exit out of this, this document here. Alright. I'm gonna go ahead and kind of clear this.

Jordan Wilson [00:30:25]:
Alright. We're gonna give it

Jordan Wilson [00:30:26]:
a minute. We're gonna give it one more, one more kind of, one more run here. I'm gonna clear the cache. So I'm I'm essentially clearing everything. Right? I'm gonna go ahead also and reload this

Jordan Wilson [00:30:39]:
host. There we go. Alright. So I am I have a blank, a blanks,

Jordan Wilson [00:30:49]:
blank screen here. So now all I'm saying is I'm saying please go to the website your everydayai.com with the h t t p s. You have to include that. And I'm gonna say and find the latest episodes. Instead of saying create a spreadsheet because I just did that and it was struggling, so I'm gonna say create a Word doc, and write, basic info for the last 5 episodes in the doc. Include the episode number, title, and the description. And I'm gonna say, I'm gonna say to do this for 3 because 5, we're probably gonna write into a bunch of errors. And I'm gonna give a command that you would maybe give a, a large language model.

Jordan Wilson [00:31:34]:
And I'm gonna say, please write a witty intro, that will catch people's eyes.

Jordan Wilson [00:31:43]:
Alright. So this is the

Jordan Wilson [00:31:44]:
last demo that we're gonna do. So now I'm clicking this again. We're starting from a blank dock here. If everything works right, computer use is going to click on, Firefox. There we go. Presumably, now it's going to go to your everydayai.com. In each step, it's sending a screenshot. Right? So it knows what to do, and then it gives it the coordinates.

Jordan Wilson [00:32:09]:
Alright. It looks like it's having a problem rendering, something on our website. It made an emoji like size a trillion, but that shouldn't that shouldn't keep it from using this. So, let's see. So it ran into, it ran into an issue. It said it couldn't open, a directory file. Finally, it got it. Alright.

Jordan Wilson [00:32:35]:
So it didn't also I didn't see it go to the episodes page. Let's see. It looks like it only went to the home page. So let's see if it realizes that. So now it says, let me scroll through the episode page to gather the information about the latest episodes. Alright? But, again, for whatever reason, when I did a a demo of this earlier, right, live demos are the worst. It did fine kind of toggling between spreadsheets and Word documents and Firefox, for whatever reason, this time around, it looks like it is struggling. Right? So it is still, it's still running here at

Jordan Wilson [00:33:12]:
the top. So I just have

Jordan Wilson [00:33:15]:
to give it a second. Hey. Live stream audience. I know this one is is is going on a little bit, but let me know. Are you gonna are you gonna try this? Are you gonna use it? Or have you seen enough? Right? And you're like, ah, this doesn't really look that good. It looks buggy. But I will tell you this. I know that anthrop the anthropic team can ship, right, really quickly.

Jordan Wilson [00:33:37]:
So alright. Now now let's see what it's doing. So now it is in back into the, the document here. It's it wrote some quick recaps. I'm gonna see it here in a second. It looks like it went to the save dialogue, so it's gonna save this. It saved it as everyday AI episodes. Technically, it kept the untitled information in there.

Jordan Wilson [00:34:00]:
Let's see if this is finishing it. Let's see. Okay. So it didn't tell me that it finished yet, but it did what it it did what I asked it to. Right? It didn't format it great, but it, you you know, it says, let's see. It says your everyday AI serves up the freshest, most digestible AI insights that'll make you sound like a tech guru at your next coffee break. Right? So this is all content that Claude wrote. This isn't from our website.

Jordan Wilson [00:34:28]:
So it went to our website, looked at the home page, looked at the episode page. So then it wrote a quick recap, for the 3. So it says, episode 3, you know, and I did tell it. You know, I think I said, hey. Be witty. Let's see. What did I say? I said

Jordan Wilson [00:34:45]:
what did I

Jordan Wilson [00:34:46]:
say to the large language model? I said, please write a witty intro that will catch people's eyes. Alright. So it said episode 388, the duality of AI productivity. The fascinating exploration of how AI can both enhance and challenge our traditional notions of productivity. Discover the sweet spot between AI assistant assistance and human creativity.

Jordan Wilson [00:35:09]:
Alright. So it looks

Jordan Wilson [00:35:10]:
like it did did the job there fine. Wrote a quick recap, and then it told me here, essentially, yo, I finished. It said, I have created a Word document with a catchy intro and information about the latest three episodes from your everyday AI. The episode has been saved as, and then it gave me the name everydayai episodes dot o d t in your home directory. The document includes, then it tells me a witty introduction, information about the 3 latest episodes, and brief descriptions. And then it says, would you like me to make changes to the document, or would you like to see it in a different format? So I'm gonna try one more thing. I'm gonna say, please format the document and add paragraph breaks between the, descriptions, and I'm gonna say add more engaging content. Alright.

Jordan Wilson [00:36:00]:
I'm gonna leave that one open ended. I may or may not even let this one finish because I know this video is is dragging on a little bit. I haven't even tried this yet to see, how well it does at modifying documents that you may have it make. So, again, podcast audience. I am just typing with Claude in real time. Okay. It highlighted all of that content, and it's essentially rewriting it. Looks like it's failing again.

Jordan Wilson [00:36:26]:
So instead of an, a paragraph break, it just added it looks like a little symbol that would, in theory, denote where you would want to have a paragraph break. But it did write a lot more content. Looks like a little bit more engaging as well. So nothing nothing here, that is going to,

Jordan Wilson [00:36:46]:
you know nothing's

Jordan Wilson [00:36:49]:
nothing's ready for production. Let me just say that. We're gonna wrap this one up. I'm gonna keep an eye on it on my screen here as we wrap. But this is nothing that right now that is going to change the way that we all work. But it's laying the groundwork. Right? The fact that this technology is available right now, and I just walked you through it. Yeah.

Jordan Wilson [00:37:12]:
It took me longer than 20 minutes. You should know that now. Right? So but you can go through and follow this. It doesn't take long. Like I said, I'm gonna leave, I'm gonna leave that, kind of little piece of code both in the episode, description, as well as if you are listening here, on LinkedIn, that information should be there as well. But with very little developer savvy, right, little bit of copy and pasting, you can literally direct an AI agent. Right? It's not good right now. Don't get me wrong.

Jordan Wilson [00:37:46]:
I'll say it's downright mediocre, but it works. Right? It's buggy, but it works. Right now, anyone out there with a computer

Jordan Wilson [00:38:00]:
and a credit card, doesn't cost a lot. Right? I'll have to go check my usage. Anyone can go do this, and you can have a language model, a very capable one in clawed 3.6. We'll just call it 3.6 SONET. Come on, Entropic. Alright. So with, 3.5 SONET new, fine. You can go have it use a computer.

Jordan Wilson [00:38:23]:
And this is not the endpoint, right? This demo, this virtual machine, this is just to showcase the capabilities. This is not the end goal, right? This is just wait. Because any day now, we are gonna see developers create fully functioning, robust, polished tools. That's what this is all about. It's giving businesses, developers, third party software providers access to this technology. Right? This clunky demo is just a clunky demo. Right? This isn't the end use, but y'all, AI agents are coming. I can't even say they are coming.

Jordan Wilson [00:39:03]:
They are here. I literally just walked and talked you through it on a live stream. And you don't need to have a technical background. You don't need to be a coder. All you need to do is to be able to type to a large language model. It's pretty exciting. Alright. I hope this was helpful.

Jordan Wilson [00:39:20]:
If so, please go to your everydayai.com. Sign up for the free daily newsletter. Also, tell me, what else do you wanna what else do you wanna see? What else do you want to to hear? I did this because a lot of y'all, after we covered this last week, they said you said, hey, Jordan. I know it might be a little more technical, but do, you know, do a demo. Show us how to use computer use. So here you go. You want it. You get it.

Jordan Wilson [00:39:40]:
What do you wanna hear next? Thank you for tuning in. We hope to see you back tomorrow

Jordan Wilson [00:39:44]:
and every day for more everyday AI. Thanks, y'all.