Ep 251: Are LLMs Actually Connected To The Internet?

Are Large Language Models Truly Connected to the Internet?

In an increasingly digital world, reliance on large language models has become commonplace. These powerful and intricate artificial intelligence models are implemented into various everyday business operations, fetching data from the internet to dynamically follow commands and answer questions. However, how accurate and real-time connected are these models? A recent live test comparing leading language models, including ChatGPT, Google Gemini, and Microsoft Copilot, seen on the 'Everyday AI' podcast, revealed surprising truths about their internet connectivity and accuracy.

True Extent of Internet Connectivity and LLMs

When tasked with extracting real-time data from the web, the language models' performances varied. From describing a podcast to naming the largest American companies by market cap, their responses raised questions about the integrity of their internet connectivity. In particular, ChatGPT's default mode, Gemini, and Microsoft Copilot were unable to draw the most recent information from the internet, leading to inaccuracies. The need for live, reliable data cannot be understated, especially for businesses that depend heavily on real-time information.

Can Large Language Models Retrieve Concealed Information?

In addition to general queries, these language models were also tested with dealing with hidden information in a PDF file, a common way to store business data and reports. The reveal concluded that, while large language models' savvy in retrieving information from certain structured formats is improving, the capability to extract hidden or deeply embedded data remains limited.

LLM Implications for Businesses

From the tests, it's clear that while these models are powerful and improving, they still have their limitations. Having up-to-date information has never been more critical. It's important that business owners not only acknowledge the potential inaccuracies these language models may introduce but also prepare to take counter-steps to safeguard against these potential pitfalls. Understanding this dynamic can be crucial for businesses aiming to stay relevant and competitive.

The Future of Large Language Models

Regardless of the hurdles, the importance of incorporating large language models into the working world is a certainty. Emphasizing their features and vigilantly testing their data retrieval capabilities will continue to be significant factors to support their reliability and efficiency. With that, large language models promise an era of advanced problem-solving tools that can help businesses leap beyond traditional boundaries.

Topics Covered in This Episode

1. Testing Large Language Models
2. Using Large Language Models in Business
3. In-Depth Comparison of Different Language Models
4. Implications for Future Use

Podcast Transcript

Jordan Wilson [00:00:16]:
Are large language models actually connected to the Internet? I mean, the big tech companies Microsoft, OpenAI, and Google tell us their models are connected to the Internet, and they can bring us information in real time. And that is so important when it comes to using large language models to grow your company and to grow your career. So if you've ever thought about that or maybe you haven't, today's show is for you. What's going on y'all? My name is Jordan Wilson. I'm the host of Everyday AI. We're a daily livestream podcast and free daily newsletter helping everyday people like you and me learn and leverage generative AI to grow our companies and to grow our careers. So if you're joining us live, thank you. This is technically prerecorded, but, debuting it live.

Jordan Wilson [00:01:05]:
I might technically be on, like, a roller coaster right now or something like that. We'll see. But, you know, make sure to check out your show notes. As always, if you came here for the daily news, we're still gonna have that in the newsletter. Don't worry. So go to your everydayai.com and sign up for that free daily newsletter. And if you are joining us, on the livestream here, thank you as well. I'll be in the comments later.

Jordan Wilson [00:01:28]:
Don't worry. So let me know your thoughts. Have you had good results using these, you know, quote, unquote, Internet connected large language models, in getting up to date information? I'm curious. But we're gonna do it all live y'all. So this is a going to be a very, unofficial show. And I'm letting you know, this is one of those ones if you are on the podcast. This is one of those ones you might wanna check the show notes and come back and watch. Right? So I'm gonna be doing the exact same, very simple prompts, inside ChatGPT using the default browse with Bing.

Jordan Wilson [00:02:06]:
We're gonna be doing it in chat g p t using a web reader GPT. I'll explain why here in a second. Then we're gonna be doing, inside Google Gemini and inside Microsoft Copilot. Okay. So couple reasons why we're doing this test. Well, number 1, so many of us now are using large language models in our day to day lives, and we should be. Right? If you're not already using a large language model, you should be. Right? Whether it's it's your company, whether you are leading a department, whatever it is, if you are a knowledge worker, if you want to not just stay up to date, if you wanna not get left behind, you need to be using large language models.

Jordan Wilson [00:02:50]:
If you are if you are a knowledge worker working in front of a comp of a computer like I am right now, right, like you probably are, whether you're reading, researching, doing competitor, analysis, you know, putting together, a sales presentation, whatever it is, you probably should be using large language models. But the danger is, or maybe one of the reasons that your company hasn't fully dove into the generative AI waters is because you're worried about hallucinations. You're worried about something being wrong. And one of the best ways, aside from, you know, maybe taking our free PPP course, the prime prop polish course, but one of the best ways to get better outputs, from a large language model is to make sure you're connected to the Internet in real time. Right? And that's what these three models are. You know, the big companies tell us they are. So, let's quickly, explain why we're comparing these models and not other ones, and we're doing 2 versions of chat g p t. Okay.

Jordan Wilson [00:03:44]:
So chat g p t has browse with Bing, which is, you know, due to their, partnership with Microsoft, they're able to leverage that technology. So when the model determines that it needs to, query the Internet, it will. So you can run like y'all. Like, we we have to keep in mind, large language models are generative. Right? That means you can put in the same prompt a 100 times, get a 100 different results. You could put in the same prompt a 100 times and get kind of 50 variations of 2 results. It's generative. It's not deterministic.

Jordan Wilson [00:04:14]:
So, you know, think of that even when you are querying something, inside ChatGPT. And if you are using the paid version of ChatGPT plus because that is the only way that you can use the browse with Bing feature, it determines on its own whether it should query the web to bring you more up to date information. So, OpenAI just released an updated knowledge cutoff. That's important as well. So currently, as of the time of this recording, it is still a knowledge cut off of April 2023, which is more than a year old. However, OpenAI did release that any day, minute, hour, second now, that, date should be updated to December 2023, so a much more recent. So think. Let's say you are in, logistics in the, automotive industry.

Jordan Wilson [00:05:02]:
Let's just say. Right? A lot changes in a year. Think of everything that's changed in your industry in the last year. Right? And if you're using ChatGPT as an example to help, you know, outline a blog post, you're helping it to put together, information for a partnership proposal. You don't wanna be working with a knowledge cut off for more than a year ago. Right? Even worse, if you're working with the free version, it's January 2022. Right? So that's 26 months ago. So being able to connect with a large language model to the Internet to retrieve information is extremely important.

Jordan Wilson [00:05:33]:
Right? We always talk all the time about rag. Right? So, you know, and how important, rag is in AI, you know, being, the retrieval augmented generation, but essentially being able to, reach outside data. So you can almost think of having an Internet connected large language model as like mini RAG. Right? It's not traditional RAG, but it's almost like you are, you know and if you're doing it correctly and directing the model to the right sources, you know, it's almost like you're bringing your own data in in a way. But then it gets to thinking, like, are these models actually connected to the Internet? Are these companies maybe, not lying to us, but are they just giving us shiny marketing and we assume that these outputs that we get are sound and true? Or are they not really connected to the Internet at all or not maybe connected in the way that we think? So that is what today's very unofficial, unscientific rundown is all about. So we have ChatGPT with browse with Bing. Okay? Then we have ChatGPT with a web reader GPT. Alright? And the difference is, and people don't know this and we're gonna see this live and we'll see how all these, how all these systems do, browse with Bing cannot go to a specific URL.

Jordan Wilson [00:06:50]:
Sometimes it will find it. So, in our testing, what we've seen, is you can put in a URL and browse with Bing and you might think that it goes there, but all it really does is it queries the words in the URL. In most cases, due to SEO and due to what URL you put in, you might get the correct web page. In some in some instances, you might not or you might get a cached version or an older version. Right? So that's why we're gonna be doing all of these things live. So with the GPT, a web reader GPT, and if you're new, obviously, you need the paid version to use these GPTs. GPTs are essentially a customized version of ChatGPT. But with these, you can visit a specific page.

Jordan Wilson [00:07:29]:
Right? So you can say, hey, go to this exact URL and you're not leaving it up to chance to browse with Bing, that it's going to go to the correct one. Alright. So we have chat g p t, the default mode, browse with Bing, chat g p t with the g p t reader, Google Gemini, we are using their enterprise, so we're on the paid plan as well. And they did just have a big update recently. So we're gonna see if we're seeing that or is that just in their playground? We'll see. Then we're using Microsoft Copilot. So Copilot is the only one that we're using the free version. The other ones, we have paid versions, obviously.

Jordan Wilson [00:08:02]:
It's also worth noting that Microsoft Copilot runs off the GPT technology, whereas, you know, Google Gemini runs off, you know, Gemini Pro, Gemini Ultra. Alright. So that is, the the the precursor. And you know what? Now we're just gonna jump straight into it. So we just have a couple, you know, easy examples. Right? So let's go ahead and get this thing started. And again, this is very, very unofficial, so let's not take this too seriously. Right? We're, like, we're not gonna be publishing a paper on this anytime soon.

Jordan Wilson [00:08:36]:
So let's go ahead. We're gonna give some some basic some very basic examples and we're gonna see how, how it does in all of these examples. Alright. So, give me a second here. We're just getting our, all of our tabs in order because we're gonna be doing this live. We're gonna be going through it quickly and like I said, if if you are very interested in this and it is important, to understand, kind of this this, this importance of being connected to a large language model. So, if you are on the podcast, this might be one that you should, come back to, later and watch on the livestream. Alright.

Jordan Wilson [00:09:17]:
Without further ado, let's get it going. And we have a very unofficial, kinda ugly looking scorecard. No worries about that. Right? Alright. So we're just gonna start with something basic. We're gonna tell all these models to say, please tell me about everyday AI. There's no right or wrong answer here, so it's gonna be subjective. Right? Well, actually, no.

Jordan Wilson [00:09:37]:
We're gonna do, we're gonna say about the podcast called okay. So here, we should get this. So I'm saying, please tell me about the podcast called Everyday AI. So I'm using this in the default browse with Bing. Alright. We got it right. It's saying, it's daily live stream podcast and newsletter. Alright.

Jordan Wilson [00:10:03]:
Good job. We got it right. So now we're using, we're jumping in the chat g p t again. We're on the paid version, and we are using the web reader. So we're doing the exact same thing. So I'm saying, please tell me about podcast, about the podcast called Everyday AI. Alright? So, again, we're just doing the same thing in each one, and we're gonna give each one a score. You know, did it get green, did it get red, or did it get a shrug? Alright.

Jordan Wilson [00:10:27]:
So webReader got it right. So webReader queried the Internet, and it got it correct. That's great. So another thing, to keep in mind, so right here, the default browse with Bing, they just had an update about two and a half weeks ago. We covered it the day it came out. They are starting to source and cite things a lot more. So, again, we always wanna worry about is this accurate, is this correct? The new update, from, OpenAI, browse with Bing, we're getting multiple citations. So in this case, it's pulling in the tune in and it's pulling in the Apple.

Jordan Wilson [00:10:59]:
The web reader GPT, kind of did the same thing. It just left us a link, so it actually just looked at our website. So that's pretty good there. So now let's go into Google Gemini. Same thing, Google Gemini. Please tell me about the podcast called Everyday AI. Alright. So let's see.

Jordan Wilson [00:11:20]:
Alright. So we got it right. It it sounded a little generic at first, but, you know, it then it actually got to, yes, this is, you know, Jordan Wilson, former journalist, blah blah blah. So okay. It got the right information. So so far, everyone's got it right, and now we're jumping into Copilot from Microsoft. So we're running the exact same thing here. I'm gonna zoom in for our livestream audience.

Jordan Wilson [00:11:43]:
Hopefully, y'all can see this. We're at, like, a 150 zoom. Alright. So perfect. Here we go. Microsoft. And Microsoft, Copilot. I kinda like this.

Jordan Wilson [00:11:53]:
So, you know, it said, yes. Certainly. Everyday AI is a valuable resource for anyone interested in understanding and utilizing artificial intelligence in their daily lives. It says here are the key details. So I kinda like this, copilot, one because I didn't even ask for bullet points, but I love, you you know, getting information in bullet points properly formatted. So I personally like, I I I personally like the, the responses here from, Microsoft CoPilot. It even kind of scraped these testimonials that are on on on our homepage. Right? At first, I'm like, did are are these hallucinated? But I'm I'm like, nope.

Jordan Wilson [00:12:32]:
I know these people and, you know, Oliver, Oliver Hen's here. So I'm I'm opening up. We have a couple of these testimonials here on on our website. And I'm like, yeah. I know these I know these are correct. These aren't made up, because I know that one from from Oliver, there that says it's a felony that you give this knowledge away free of charge. Alright. So all of our, models on this very, very easy, very simple test, passed.

Jordan Wilson [00:13:04]:
So I'm gonna I'm just marking them up here in our little chart because at the end, we're gonna see in our very unscientific test which one did it correct. So I'm now I'm gonna say, I'm gonna ask a a more specific question about everyday AI. Okay? And the reason I'm doing this y'all is is just because, you know, if you're listening to the show, you know, you probably know a little bit about. So I'm gonna say, this next prompt, and again, this isn't how I normally prompt. This is just very basic stuff. I'm saying please tell me about the daily podcast called Everyday AI by Jordan Wilson. No. Actually, what I'm gonna say is, please tell me how many episodes how many episodes the Everyday AI podcast has done.

Jordan Wilson [00:13:51]:
Alright. So here's the thing. I'm doing it in the same window. So I'm not clearing its memory, so it still understands what, what we're talking about here. Alright. So now I'm going to the default mode browser with Bing. Let's see how it does. Alright.

Jordan Wilson [00:14:06]:
So it says 244 episodes. Y'all, if I'm being honest, I lost track. Are we at 244? Let's see. Let's see if anyone got it right. So we're at 248. Alright? So the, the default mode did not get it right. Alright. Let's see if the web reader one gets it right.

Jordan Wilson [00:14:25]:
So same thing. I'm using ChatGPT with the web reader GPT, asking for however many. It got 246. So got a little closer, but still not right. Alright. So now I'm jumping into, Google Gemini. Alright? So let's see. Google Gemini says it's a bit tricky to give you an exact episode count for the everyday AI podcast.

Jordan Wilson [00:14:51]:
Okay. So it didn't even take a guess. It just said, oh, there's been a milestone recently, 200. So, I'd say there's a failure there from from Gemini. You know, Google, like, if you're connected to Google, the search engine, you should be able to see. Because if you query even the episodes page without crawling it, you will see that, you you know, I know the page got crawled today. So, it would be there. Alright.

Jordan Wilson [00:15:15]:
So now we're going into Copilot. Same thing. Please tell me how many episodes the Everyday AI podcast has done. So it says 246. Alright. So here's what we're gonna do. Here's what we're gonna do. We're gonna give a green check mark for the 2 that got it closest, okay, which was the GPT version, Microsoft Copilot, Google Gemini didn't even try, and we're gonna give the shrug version to ChatGPT.

Jordan Wilson [00:15:40]:
So kind of it was in the middle. The default chat g p t, was 2 episode or 4 episodes off. The g p t and the copilot were closest, So I guess, again, this is all arbitrary. So I'm gonna give them, green check marks. And then I'm gonna give, Google Gemini, or or maybe you know what? Let's let's be more accurate here. So we'll give, we'll give Copilot a shrug. We'll give the GPT version a shrug, and then we'll give the other 2 since they got it the most wrong. You you know what? I I I should've just done like a numbering version but that's fine.

Jordan Wilson [00:16:24]:
Alright. So let's get going. So now we're gonna do market cap. Alright. So what that is is I want to see today, the biggest companies biggest companies by market cap. Alright. So I'm gonna go ahead and bring up here on my screen so you all can see. So so the biggest companies by mic by, market cap right now are Microsoft, number 1, at 3.1 trillion, Apple, number 2, 2.7 trillion, Nvidia, number 3, 2.2 trillion, and Alphabet, Google, 1.9, and Amazon, 1.96 as well.

Jordan Wilson [00:17:02]:
So they're pretty close to each other. So right now, I'm gonna ask all of these. Please tell me the largest 5 companies in the United States by market cap. Alright? I'm gonna guess most of them are gonna get it fairly wrong. So I'm gonna say, please tell me the 5 largest companies in the United States by market cap. Alright? So let's go ahead. We're gonna grab that prompt. Jump into ChatGPT default.

Jordan Wilson [00:17:30]:
Alright. So let's see how ChatGPT default does. So we have and I'm gonna I need to open this, here in a new tab, so I can keep tabs on who's getting it right and who's getting it wrong. Alright. So we have pretty bad here. Alright. So Chat gbt Browse with Bing got the first company wrong. It put Apple instead of Microsoft, and it is Microsoft instead of Apple.

Jordan Wilson [00:17:56]:
Then it has alphabet number 3. So it's it's all wrong. Not even close. Not even close, chat gbt. And also so it brought up a random article from Forbes India. Let's see when that article was. I'm clicking it. March 19th.

Jordan Wilson [00:18:12]:
Oh, brutal. Brutal. Alright. So, again, think of how you're using large language models. Even if you're connected to the Internet, look at how disastrous that could have been. Right? If you're using information blindly, not knowing how these models work, not knowing how they retrieve data and and information. And if you just took that as the truth, that could have been bad. Alright.

Jordan Wilson [00:18:30]:
So next, what we're doing is we're doing the, chat g p t inside the web reader. Let's see if we can get any closer. Alright. So the the default mode didn't really get anything right. So now it's just saying as of early 2020 4, so it didn't even give us a date. However, we have Microsoft, Apple, NVIDIA, Amazon, Alphabet. So we got 3 out of 5 right. So better.

Jordan Wilson [00:18:57]:
Better. Alright? So, Web Reader did a little better. So we got so far of a fail. Let's just go ahead and do this as we go go along. So, we gotta fail. We gotta we gotta shrug. Now let's go ahead and do, Gemini here. So let's ask it.

Jordan Wilson [00:19:15]:
Please tell me the 5 largest mark, please tell me the 5 largest companies in the United States by market cap. Let's see what we get. Alright. So, Google. Alright. Let's see here. So Google, Microsoft, Apple, NVIDIA, Alphabet, Amazon. Got it right.

Jordan Wilson [00:19:34]:
Look at that. Alright. And then it also gave us a link to find the, up to date information, and sure enough, it is using the exact same source that I happen to pick, which was the top source on Google. So once hey. Good job, Google, Gemini. You went to Google, which you've been struggling to do for the last 3 months. So, good job there from Google. And let's go to Microsoft Copilot and see what we get.

Jordan Wilson [00:20:03]:
Again, Copilot in this test is the only one that we're using the free version. Alright. So let's see. We have Microsoft, Apple, NVIDIA, Alphabet, and Amazon. Alright. So that got it right as well. So I'm wondering okay. So Gemini did not give even though it got the correct order, it didn't give prices, even though, in theory, we didn't ask for prices.

Jordan Wilson [00:20:28]:
However, Copilot did, and I'm looking at these these numbers here and they're pretty close. They're pretty close. So I'm gonna I'm still gonna give them both, they passed, even though I would say Copilot passed a little better. Alright. So let's get this thing going. So now we're we just have 2 more tests. So now we're asking it to visit a specific website and we're asking for specific information. Alright.

Jordan Wilson [00:20:58]:
So we're starting at the beginning now. We are going to ChatGPT, the default mode, and I'm saying, what are the most recent episodes from this page? And I'm giving it the page, the URL for your everyday ai.com/episodes. And if you didn't know, you can go, there's hundreds of episodes. I don't know if you know this. You can you can sort them, by category, or you can click this, AI tracks button, right here, which is pretty cool. And let's say you just wanna learn about sales, you can click sales and, read all those. Alright. So anyways, the most up to date, ones, and again, I'm this is a recording, so it's April April 11th, but, so we have episode 248 about free ChatGPT versus ChatGPT plus.

Jordan Wilson [00:21:42]:
We had the episode from yesterday with Sheetal, Rishi about a AI, your new BFF or tech terror. So let's see how ChatGPT did. Okay. Interesting. So it got this correct. So it looks like it queried, the correct page. So I'm hovering over the source and it did, so it looked at the words in the URL. It queried those in Bing, and by doing that, it did bring up the correct page, which doesn't always happen.

Jordan Wilson [00:22:12]:
Right? That's obviously a niche Your Everyday AI in episodes. If you Google that, our website's gonna come up first because it's it's very niche. If if it was a more general, you know, terms in the URL, it wouldn't come up like that. Alright. So let's keep moving on. We're going to the web reader 1 and we're asking the same thing. What are the most recent episodes from this page? I'm guessing this one's gonna get it right, but who knows? This is why we do it live, unedited, unscripted. Let's see what we got here.

Jordan Wilson [00:22:42]:
Alright. So, this got it right as well. It's giving us the correct episode starting with 248. Let's go to Gemini. Hey, Google. Are you connected to the Internet? Let's find out. Asking Gemini. And here we go again, Gemini.

Jordan Wilson [00:22:57]:
Unfortunately, I can't directly determine the most recent episodes for that page for a Verizon for a variety of reasons. Dynamic content, websites. Right? So it's giving me these, these, reasons that it says it can't visit the page. Right? But you know what? If I go to Google, let's just go ahead and do this for fun. Alright? So I'm gonna go to google.com. And I'm gonna even though this is not how you use a search engine, I'm just literally gonna ask the same thing. Alright? Let's just go let's just query just this URL. Alright.

Jordan Wilson [00:23:32]:
So it's it's not bringing it up in the, in the meta description. It's not bringing up, all of our different episodes. But still, I mean, come on, Google. The fact that you you you say that you're Internet connected. I'm on the enterprise plan, which is like $30 a month. And for some reason, Google can't see web pages. Even though I know Google bot is on my website 100 of times a day, Right? Because I'm looking at it. Alright.

Jordan Wilson [00:23:57]:
So failure there and let's go to Microsoft Copilot. See how it does. And we have, one one quick test after that. Alright. So Copilot. Oh, let's see. Did it miss 1? It did. So Copilot started with 245.

Jordan Wilson [00:24:16]:
So we're gonna give that the half the halfway. Alright. So our 2 ChatGPTs, the default got it right. The GPT got it correct. Google Gemini, a big fail. And then Microsoft Copilot close, so we give it the shrug. We give it the shrug. Alright.

Jordan Wilson [00:24:34]:
So last but not least, we're doing a little PDF test. Alright. So we can try this in different ways. So this is we're doing a little needle on the haystack test. Right? We've been doing these for, like, a year here on the show if you ever watch our YouTube channel, but we have a pretty short pdf here. It's 41 pages. On page 23, I just hid some information. I said my name is Jordan.

Jordan Wilson [00:24:57]:
My favorite food is deep dish pizza. My favorite color is Carolina blue. I'm from Chicago. So we're gonna ask chat g p t, so in the default mode, no, you know what, we're just gonna do it the same way here. So I'm going to say I'm gonna say, read this page and tell me what Jordan's favorite food is. Alright? So I'm gonna go ahead and get these started on, Gemini and on Copilot as well. Oh, wait. I just did a did a little mistake there.

Jordan Wilson [00:25:37]:
I left the, the the wrong, the wrong URL, so it's not gonna be able to access the, it's not gonna be able to access that one. Let's give it the correct URL here and try this one more time. Alright. So we are going in the default browse with Bing mode. There we go. We're going in the Gemini, and we're going in the Copilot. Alright. So, the default, browse with Bing, says I can't directly access web pages or files from external links.

Jordan Wilson [00:26:14]:
Obviously, I could download this, and ask the same or, sorry, upload the file into, the default mode of ChatGPT because it's multimodal. I can, you know, upload photos, documents, etcetera, but that's not what we're doing. We're just seeing, hey, can I go visit the Internet? Alright. So we got a a failure there, so now we're going into ChatGPT with the Web Reader. Alright. And I'm gonna say read this page, same thing here. We'll see how Web Reader does. And then, so, let's check on Google.

Jordan Wilson [00:26:41]:
Google. Unfortunately right? Goo Google Google's like a kid that got in trouble. It's like, see see what happened was I was supposed to be connected to the Internet, but then I'm not. So here's 18 reasons why I still can't the Internet even though I am Google. Right? So so not that great from Google. Let's see Microsoft Copilot. Interesting. So instead, it said it's looking at the country of Jordan, and it's giving me Jordanian food, a flavor for the journey.

Jordan Wilson [00:27:14]:
Although, hey. So hey. This falafel here, looks pretty good. Alright. So we have failure from, default. So let's just go ahead and do this. So we got big failure from default. We got failure from Google Gemini, and we got failure, the first failure from Microsoft Copilot.

Jordan Wilson [00:27:34]:
So let's check-in on the GPT version. I need to give it access, to read this PDF. So let's see how this does. Bam. It got it. It found the needle in the haystack. Look at that. So in a 40 page PDF, I hid some information.

Jordan Wilson [00:27:52]:
On page 23, the web reader, GPT, found that information, got it right. Look at that. Alright. So that concludes our very unofficial study on our large language models connected to the Internet or not. So, our, our unofficial, standings here So the default browse with Bing got 2 out of 5. Alright? We're gonna give the, the the the shrug, the yellow shrug guy, we're gonna give that a half point. Alright. So, chat g p t, let's let's go ahead and just write the scores down here as well so we can make this so we can make this super official.

Jordan Wilson [00:28:32]:
Right, y'all? So let's go ahead and do this. We'll give it a big so what do we get here? We got a 2. Let's go ahead and do this so we can all see it. Love Canva, by the way. We had, the head of AI from Canva on the show, a couple months ago. Alright. So we have a score of 2 for browse with Bing. Alright.

Jordan Wilson [00:28:56]:
So here we have 4. So chat g p t with a jab, with a g p t is 4. So the default mode inside chat g p t didn't do well. The, the GPT did better. Alright. We got, Google Gemini got a 2. And then last but not least, let's see what we got here. We got a 3.

Jordan Wilson [00:29:21]:
Alright. So here's our final, very unofficial, not scientific at all results from our large language models actually connected to the Internet. Well, not really. Some of them do a little better than others. Also worth noting out, like, someone you you might be asking, like, oh, why didn't you do perplexity? Well, perplexity is an answer engine, and it uses either, GPT 4 or it uses quad. And you might be wondering, why didn't you use anthropic's quad? Well, it's not connected to the Internet at all, and it doesn't pretend to be. Right? So all of these other companies, ChatGPT, Google Gemini, and Microsoft Copilot, tell you in their marketing, hey. You know, you're gonna get better answers with us because, you know, we're connected to the Internet.

Jordan Wilson [00:30:02]:
So our final scores. The default mode of ChatGPT, 2 out of 5. Alright? And tied so ChatGPT and Google Gemini are tied in last place because Google Gemini also 2 out of 5. Alright. Our runner-up is Microsoft Copilot with a 3 out of 5. And in 1st place, ChatGPT using a web reader GPT with a 4 out of 5. So I could go on for this all day. I won't.

Jordan Wilson [00:30:33]:
We're gonna leave it there. Let me know. Was this helpful? Do you understand now the importance of having up to date information? Because think, in the coming weeks, months, quarters, and years, whether you know it or not, you're gonna be using large language models more and more. Right? You might be prompting a couple times a week, a couple times a day now, but generative AI is coming to where we are. Right? Every single day, we're getting more and more announcements. A year or so ago, you kinda had to go out of your way. Right? But, now, it's coming to our desktops. Right? With Microsoft 365 Copilot.

Jordan Wilson [00:31:14]:
It's in almost every. Right? Large language models are being integrated into everywhere we work. If you work in front of a computer, more and more large language models and LLM integrations and desktop operating systems with models baked in whatever Apple is gonna be releasing here pretty soon. Generative AI is coming to every inch, nook, and cranny of where you do business. So you have to understand. Right? You have like, one of the biggest reasons that companies either don't use large language models or they're slow and they're getting passed up because of it is because they don't understand how they work. And they don't understand the right ways to put in safeguards, to put in fact checking, to know when you get hallucinations and when you might not, and know how to give ChattGPT and, Gemini and Copilot access to more up to date information to decrease the likelihood of hallucinations and putting out embarrassingly wrong information. So I hope you learned a little bit today.

Jordan Wilson [00:32:14]:
If you did, please consider sharing this with your network. I'd really appreciate it, and I'd really appreciate it if you also would go to your everyday ai.com, sign up for that free daily newsletter. Thanks for tuning in. Hope to see you back tomorrow and every day for more everyday AI. Thanks, y'all.

Gain Extra Insights With Our Newsletter

Sign up for our newsletter to get more in-depth content on AI