Ep 246: No that’s not how ChatGPT works. A guide on who to trust around LLMs

Episode Categories:

Harnessing the Power of ChatGPT: Redefining Business with Large Language Models

Every entrepreneur, business leader, and decision-maker is looking for ways to optimize their business operations. In the digital age, this often means turning to AI-powered solutions. ChatGPT and other large language models (LLMs) have emerged as highly promising tools, but misperceptions about how they work and what they can do have prevented many from utilizing their full potential. Contrary to prevalent beliefs, the basic, free versions of such tools are not equipped for effective business use. Instead, robust, paid versions such as ChatGPT Plus with GPT4 offer extensive capabilities that can foster significant business and professional growth.

Critical Approach to Information and AI Tools

In the rapidly evolving digital marketplace, the sources of information and tools used greatly matter. Although popular, platforms such as Bing can sometimes return outdated information that can skew business decisions and strategies. Similarly, the use of generic prompts for business engagement is proven ineffective and often harbours the risk of personal information exploitation for marketing purposes.

Dismantling Misconceptions about AI

One commonly encountered misconception is that copying and pasting a writing style into a tool like ChatGPT will enable it to mimic that style effectively. However, GPT models function by tokenizing words and don't truly comprehend them. Misleading information about AI capabilities can impede businesses from maximizing their use and could lead to reputational risks.

Tailoring AI For Business Needs

Successfully harnessing large language models for business activities such as copywriting requires precision and the right guidance. Recent examples include the use of an expert chat for model training, leading to large volumes of conversational data. Armed with these data, AI can turn out impressive, targeted outputs - surpassing even human-written ad copy in some instances. However, constant training and iteration are required for refining large language models to benefit specific business needs.

Balancing AI Dependency

While AI tools present significant opportunities, complete reliance should be avoided. Platforms like ChatGPT, backed by large search engines, might not always yield timely or accurate results, particularly in a dynamic business environment. This is due to possible SEO manipulation that can impact the information generated by these tools.

Harnessing ChatGPT

There's no doubt that large language models have a place in modern business strategy. To tread on this path, leaders might consider participating in courses tailored to help users learn how to maximize the tools like ChatGPT. Real-life examples from successful entrepreneurs underline the usefulness of large language models when utilized correctly. Post-taking such a course, refined 'prompting' and coaching protocols for AI models can lead businesses to harness the true power of AI.

Last but not least, with the benefits come the risks of using large language models. Users are advised against sharing screenshots of unpolished AI outputs and to remain aware of the dangers associated with incorrect AI usage. The key to successful AI implementation lies in understanding its potential and use-cases and using it within precise parameters that ensure both effectiveness and security.

In word and spirit, large language models are more than just tools; they are business allies. It's about time we treated them that way. To stay at the forefront of the AI revolution, it's crucial to debunk the myths, gain the right insights, and leverage AI to its full potential. Remember, it's not just about having access to AI; it's about using it correctly to gain a competitive advantage.

Topics Covered in This Episode

1. Overview of ChatGPT
2. Misconceptions around ChatGPT
3. Usage of Generic Business Prompts
4. Superiority of Large Language Models
5. Risks of Sole Reliance on Tools like ChatGPT with Bing

Podcast Transcript

Jordan Wilson [00:00:17]:
No. That's not how ChatGPT works.

Jordan Wilson [00:00:22]:
Whether you're browsing

Jordan Wilson [00:00:25]:
social media, looking something up on YouTube, or maybe you're hearing this from a friend. But there's so much bad advice out there about ChatGPT and people talking about what it is and what it isn't. Well, I'm here today to chop down some of those rumors, to cut through the fluff and tell you what ChatGPT is and what it isn't as we go through some of the most common things that people get wrong about most people's favorite large language model. Alright. 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. This is for you and me.

Jordan Wilson [00:01:08]:
How we can all learn generative AI and leverage it together to grow our companies and to grow our careers. So if that sounds like you and if you want to know a little bit more about chat gbt, whether you are brand new or you're using it every day, I think today's show is going to be for you. Actually, no. I know today's show is gonna be for you. Alright. So, super excited to talk about that. But if you are listening on the podcast, make sure to go to your everyday ai.com. Sign up for that free daily newsletter.

Jordan Wilson [00:01:35]:
We'll be recapping today's show as well as a lot more. You're not gonna wanna miss today's recap, talking about what chat g p t is and what it isn't. Alright. So before we get started, let me just tell you, at the end of the show, we're gonna be announcing our GPU giveaway from NVIDIA. So if you entered, make sure to stick around to the end of the show. We're gonna be announcing that live here and in the newsletter as well. Alright. Before we get started, let's talk about what's going on in the world of AI news.

Jordan Wilson [00:02:07]:
So the US government is investing 6,600,000,000 with a b, $1,000,000,000 in semiconductor chip manufacturing in Arizona. So the US government plans to provide $6,600,000,000 to Taiwan Semiconductor Manufacturing Company, which is TSMC, to build 3 semiconductor chip fabrication plants in Arizona. So president Joe Biden aims to secure the supply of advanced chips, highlighting the economic and national security vulnerabilities of the US due to decreased chip production capacity. So TSMC's investment of $65,000,000,000 in Arizona includes the construction of 3 fabrication plants or fabs as they're called, and it marks the largest foreign direct investment in the state's history. Alright. So the 3 fabs are expected to create around 6,000 high wage tech jobs and 20,000 indirect jobs contributing to the local economy and the job market. This move reflects the US government's emphasis on onshoring chip production to reduce supply disruptions, particularly after experiencing bottlenecks during the pandemic. So this investment will enable the US to domestically produce the most advanced what they're saying is the most advanced semiconductor chips, enhancing supply chain resilience and reducing dependency on foreign manufacturers.

Jordan Wilson [00:03:26]:
Alright. Next piece of AI news, Google has enhanced its workspace with some new AI capabilities. So let's take a quick look. So Google has introduced new generative AI features to Workspace, enabling users to create collaborative videos for storytelling. So this move aligns Google with competitors like Microsoft 365 and Cisco Webex, enhancing workplace productivity and collaboration. So the new real time video collaboration feature in Workspace leverages Google's AI research and video expertise for advanced presentation storytelling. Google is continued is continuing to integrate AI capabilities from Gemini into workspace applications like Docs, Sheets, and Gmail, enhancing communication and collaboration. So this new all in one video editing and writing production assistant should be seamlessly integrated with other productivity tools inside of Workspace.

Jordan Wilson [00:04:22]:
So if you use Workspace like our team does, make sure to go check that out. Last but not least in AI news, more Google news and more processing. Right? So Google has introduced its first custom built ARM processor called Axion based on ARMs, the company ARM, the manufacturer, based on ARM's Neoverse 2. So Axion instances offer up to 30% better performance then competitors ARM based instances and up to 50% better performance, and 60% better energy efficiency than comparable x 86 based instances. So Google did not provide detailed documentation to support these new claims, but mentioned that technical documentation will be available later this year. Google emphasized that Axion is built on an open foundation allowing customers to bring their existing ARM workloads to Google Cloud without modifications. So, yeah, a lot of chip in processing news today y'all, but it's pretty big. I think the world has figured out including the US government as an example, you know, pairing up with TSMC.

Jordan Wilson [00:05:26]:
You know, I think everyone's realized just how far ahead NVIDIA is. So a lot of, investments here, to increase manufacturing for these AI chips, these GPUs that really power all of the generative AI tools that we all use. Alright. Let's get into it. Let's talk about reasons. No. That's not how Chat gbt works. I've just been seeing too much nonsense lately, y'all.

Jordan Wilson [00:05:51]:
Like, every, I don't know, every month or 2, I just see so much bad information, and sometimes it is very smart people sharing bad information. So I wanted to go over some common misconceptions, and, essentially, if you are hearing these things that we're gonna be going over, you know, if you hear people telling you this, right, whether it's someone you follow online, whether it's it's it's a coworker, maybe it's an outside consultant that your company is bringing in to help you with your generative AI. If you hear these things, run for the hills. Avoid their advice. Ask more questions. Alright? So these are some telltale signs that someone probably has little to zero clue on what they're talking about when it comes to ChatGPT. Hey. And let me know.

Jordan Wilson [00:06:36]:
Some of y'all, like like Tara, who's joining us live and and Brian, have already told me about how hot should we make it. Y'all sometimes the more tired I am, the the the hotter these takes get. So let me know. Drop a couple flame emojis. Encourage me to either come with hot takes or to to take it nice and easy because, you know, maybe, maybe it's it it is call out time. Maybe it is call out time like Woosie Rogers says here, on the livestream. So thanks to our, live crew for joining us. And as a reminder, if you are joining us on the podcast, check out your show notes.

Jordan Wilson [00:07:07]:
If you wanna come join the live stream, so many great, AI enthusiasts, leaders who are implementing generative AI at their companies to, connect with here. Alright. So let's get it started. Let's get it started, y'all. Ready? So people have ChatGPT all wrong. A lot of people talk about ChatGPT like it's just some copywriting tool. That is literally not what it is. That is furthest the furthest thing from the truth.

Jordan Wilson [00:07:32]:
I like to call ChatGPT a business operating system. Okay? Which is a little different. I I think that right now, ChatGPT is the only business operating system. I think Google Gemini, is is close to being there, but they're having problems connecting workspace data with enterprise accounts and with paid accounts. So I don't think, you you know, Google Gemini is there. Oh, no. I I'm wrong. I will say Microsoft Copilot is there.

Jordan Wilson [00:08:00]:
Sometimes I think of Copilot and ChatGPT as one one and of the same. Right? So, I I think you have Microsoft Copilot, that is a business operating system. I think you have chat gbt. I think that Google Gemini is close ish, and I think that Claude once Claude, kind of, enables third party tools in their chat interface, face, right, which we talked about on the show that they enabled it for developers, recently. But once they enable it on their chat interface, we'll get there. But today I'm just talking about chat gbt because I think that is probably the the the most, you know, the most capable and the most popular large language model by far. So that's what we're talking about today. Alright.

Jordan Wilson [00:08:42]:
So as a reminder, our team has been using the GPT technology since 2020. Right? So, yeah, especially once ChatGPT came out in November 2022 and as it's become more popularized, we're just seeing more and more bad takes from people. So here's here's the first one. Here's the first one. It is call out time. It is call out time. So people who share a chat g p t response, and they say, hey, ChatGPT is no good. Look at this response.

Jordan Wilson [00:09:12]:
And then they share a screenshot. That is not how ChatGPT works. If you're sharing a low quality output, sorry not sorry. That just probably means you don't know what you're doing. Hey. This is Jordan, the host of Everyday AI. I've spent more than a 1000 hours inside ChatGPT, and I'm sharing all of my secrets in our free prime prompt polish ChatGPT course that's only available to loyal listeners like you. Listen to what Lewis, a business owner, said about the PPP course.

AI [00:09:50]:
I can tell you that when I went in, I I understood a little bit about ChatGPT. I understood some of the stuff. I was able to use some of the prompts, but what I discovered going through, Jordan's webinar was that there is so much more I don't understand that ChatGPT can do, and I really should be using it. And, if anything, I got that from the webinar. I would highly recommend this to anybody from beginner to advanced. You will absolutely learn something from this from this experience.

Jordan Wilson [00:10:17]:
Everyone's prompting wrong, and the PPP course fixes that. If you want access, go to podpp.com. Again, that's podpp.com. Sign up for the free course and start putting ChatGPT to work for you. Let me repeat that again. If anyone shares, actually for better or worse, right, sharing a screenshot from ChatGPT means absolutely nothing. Right? Because in the instructions before that screenshot, you can tell chat g p t everything it needs. You can spend the time and get great outputs, or you can say nothing.

Jordan Wilson [00:10:52]:
Right? And if you just copy and paste something in, you're gonna get a bad output. Alright. So let me give you an actual example. And this is I think I'm gonna spend the most time on this one. Because people sharing their outputs from chatgpt

Jordan Wilson [00:11:09]:
is terrible. It is

Jordan Wilson [00:11:13]:
a terrible way to share about a generative tool. Right? ChatGPT and large language models are not deterministic. They are generative. So what that means, it's the exact opposite of something like Google. Right? If you do a Google search, aside from if it pulls up its new AI search, its search generative experience, it's SGE. But for the most part, a search online is somewhat deterministic. No matter who puts in the input, everyone, at least at that time and date, is going to get a similar or the exact same output. That is not how generative AI works.

Jordan Wilson [00:11:45]:
It is generative. You're going to get wildly different outputs even if you put in the same or similar inputs, and so much of it happens with what happens before you actually prompt a large language model. Alright. So here's an example. Right? I I saw a post, you know, someone posted this on social media. I'm definitely not, you know, naming names, but, you you know, I just saw this recently, and I thought this could be a good example. Alright. So the example here that we're gonna be talking about if you're joining us on the podcast, is someone was using ChatGPT essentially as a, advertising slogan assistant, for a Nike ad.

Jordan Wilson [00:12:24]:
So on my screen here, there's an actual end that I'm gonna show you. But I'm wondering which tagline or motto is the best. And this is a photo of Caitlin Clark, the, record breaking women's basketball player from Iowa who broke the n c double a scoring record, in in a very triumphant pose. Right? So she has her hands up in the air kind of looking to the side. Very great photo. So what for our live audience, let me know which one of these is

Jordan Wilson [00:12:52]:
the best tagline. Ready? Or you can play along if you're if you're in the car, wherever you are listening on the podcast. Alright. So, a, which is the best tagline to go with this Nike ad for Caitlin Clark? Alright. A, breaking records and making hoops history. B, you break it, you own it. C, legends don't chase records, they set them. Alright? Live audience, let

Jordan Wilson [00:13:21]:
me know. All it takes is one little pound at the keyboard. A, b, or c. Let's try it one more time. Ready? A, breaking records and making Hoops history. B, you break it, you own it. C, legends don't chase records, they set them. Alright.

Jordan Wilson [00:13:40]:
And I'm gonna give you the answer here in, like, 2 or 3 minutes, but one of these was written with a copy and paste prompt and shared online saying, look how bad chat g p t is. Right? That's why I'm I'm going through this process and showing you how ChatGPT actually works. So one of these was done, with a copy and paste zero shot prompt inside ChatGPT. 1 was written presumably by a highly skilled human copywriter that either worked internally at Nike or that Nike hired, and one was written by Chatt GPT the correct way. Alright. So it looks like for the most part, unofficially here, c is is crushing. C is by far ahead of everything else. Right? So, let's let's keep going here.

Jordan Wilson [00:14:27]:
So this was the, well, I just I just gave you the answer of the copy and paste version of ChatGPT was actually a. So, you you know, this person on social media just said write a headline for an ad featuring Iowa basketball player, Kaitlyn Clark. She broke she broke the record for most points ever scored by an NCAA woman in basketball. Be clever. And then ChachiBT actually gave us that, number, a there or option a, which was breaking records and making hoops history. Alright. So, you can keep you can keep voting. You can keep voting.

Jordan Wilson [00:15:00]:
So we now know at least that what one of them was. But let's talk about how a prompt like that right? And again, I'm not just calling this person out. It was just a fun and timely example. A prompt like that is always going to give you bad results. Okay? And so many people, even very smart people online are just sharing cop, like, sharing copy and paste prompts. They're sharing screenshots of, hey, look at Chad gbt. It's no good. Well, if you don't use something the right way, of course, it's not gonna be good.

Jordan Wilson [00:15:31]:
If I open Google search and just pound my head on the keyboard and hit enter, I'm not gonna get good results. Okay? That is the equivalent. Y'all, large language models are not one good input, one good output. That is not how they work. A 1.8 trillion parameter large language model, which is what gpt4, which is ChatGPT's latest version, that's what it is. If you think you can just go in there, open a new chat, and type a short prompt and get something great, you're wrong. That is not how generative AI, that is not how large language models work. You have to teach them, you have to coach them, you have to give them examples, Right? We're gonna talk about that a little more.

Jordan Wilson [00:16:14]:
But zero shot prompting. A zero shot prompt is essentially when you just copy and paste something in there without examples, without going back and forth. Okay? So we have and, hey, if has has anyone out there taken our PPP course, Our our free prime prompt polish. Let me know if you have. You you know, maybe drop a line in there. But we actually did a brand new version. We blew the thing up. We've actually taught more than 3,000 business leaders from huge companies and small startups, how to properly prompt.

Jordan Wilson [00:16:45]:
Prompt engineering 101. And we actually redid the the whole thing. So we have a new process, as part of priming called refine queue. So, yeah, if you want access, just let me know. I'll send you. We're we're doing, another one here in about 4 hours. Right? So you can even join us live then. But zero shot prompting like that is always, almost always, going to give you bad results.

Jordan Wilson [00:17:08]:
So everyone, please, can you stop sharing screenshots of your results. Okay? For better or worse, that doesn't help anyone. If I'm being honest, one of the reasons I started everyday AI was yes, our team's been using the gpt technology for three and a half years and we saw that mostly everyone's using it incorrectly, but it's also very dangerous. It's very dangerous for your company if you're listening to someone who has no clue what they're talking about and you don't know. That's why I'm telling you today, no. That is not how ChatGPT works. Alright. So here is how here is the correct way.

Jordan Wilson [00:17:46]:
Alright. And if you're listening on the podcast, I'm sharing something with our livestream audience, livestream audience. I did this last night. This is prime prompt polish. So this is our recommended way to prompt engineer any large language model, including our new refine queue method of priming. Okay. This is an example. This is a lot.

Jordan Wilson [00:18:10]:
Alright? So this is 6,000 tokens or about 4,500 words to build a Nike focused slogan writer. Alright? And, hey, before anyone I don't wanna hear any, like, nonsense. They're like, Jordan. Like, you you wouldn't know anything. Hey. Guess what? I used to work very closely with Nike and Jordan Brand. I worked with professional athletes all the time. I worked with Nike's global head of marketing.

Jordan Wilson [00:18:38]:
I helped ghostwrite, tweets for professional athletes. I know Nike. Right? And I know what it takes to build copywriting. Right? I've I've been in, you know, martech and comms for 20 years. So this is the process that you should be going through, right? If we wanna share screenshots, let's, let's share this Because essentially, I'm showing my entire process. I did this last night. I took this. I built an expert chat, which is what we teach people to do through prime prompt polish PPP, and expert chat on writing Nike taglines.

Jordan Wilson [00:19:13]:
Right? And one of those 3 came from the result of this. 4,500 words of back and forth iterative conversation with a large language model. That is how you use a large language model. You don't just go in there, copy and paste something, or go in there and say, hey, here's some information about Caitlin Clark. Write me something, you know, from from That that means nothing. That means nothing. People don't understand. You have to refine a large language model if you want it to perform well for a specific purpose.

Jordan Wilson [00:19:46]:
That's why I'm sharing. Hey. If we wanna start sharing screenshots, let's start sharing this. Let's start sharing this, the process, the hard work, using it correctly. Right? And, yeah, if you're on the podcast, essentially, even our livestream audience can't really see anything because I zoomed out all the way. Right? And this looks like a like a 30 page book but zoomed out because that's how you do it. That is how you use a large language model correctly and get the maximum output. Livestream audience.

Jordan Wilson [00:20:15]:
Are are are you feeling this? Right. Hey. Cecilia said she she loved PPP so she needs the, the updated version. It's kind of like what yes, Ben. It's kinda like what Ben said. You know? And, Ben, I'm I'm getting out, old man Wilson here for you. You know, garbage in garbage out. Yes.

Jordan Wilson [00:20:33]:
That is the same thing. If you put in even if you put in a copy and paste prompt, you you you find something great on the Internet and you find a super long prompt. That's garbage in. You're gonna get garbage out. This is how you do it. This is how you properly prompt a large language model, specifically if you are looking for a tailored output. You gotta put the work in y'all. 6000 tokens, 4,500 words of back and forth conversation with a 1.8 trillion parameter large language model will finally get you to something good.

Jordan Wilson [00:21:07]:
A good output. Right? And I promise I promise, you know, by far. Right? I'm gonna I'm gonna go ahead and do a quick a quick count here. So it looks like we have about 8, 9, 10, 11, 12, 13, 14, 15. It looks like we had about 15 people vote for c. It looks like we had about 2, 1 no. Yeah. 1 person vote for a, and 1 or 2 people vote for b.

Jordan Wilson [00:21:34]:
Alright. So guess what? The copy and paste prompt finished last. The the the one written by a human, which was you break it, you own it, that finished second. And by far, the one that finished first with about 3 to 4 x, higher than the human copywriter was the one that I did through ChatGPT. Again, I think I had an unfair advantage. Right? I've worked with, you you know, I've I've worked with Nike, so I understand. I've created slogans with Nike. You you know? So maybe I had a little bit of an unfair advantage, but that just goes to show you a couple of things.

Jordan Wilson [00:22:15]:
Number 1, 0 shotting a large language model or just giving it no information, clicking new chat and saying, hey. You know, Caitlin Clark broke this record. Write a a cool tagline for, you know, a Nike ad. If you do that, that's a zero shot prompt. You're not working with a large language model. You're gonna get garbage. Garbage in, garbage out. The human copywriter, I'm actually surprised because I kinda like the human one.

Jordan Wilson [00:22:40]:
You break it, you own it. Right? She broke the n c double a scoring record. But, hey. At least our livestream audience said by far the best one was the one that properly went through a large language model. An iterative process back and forth teaching and training a large language model. Now guess what? If I wanted to go in there, I could spit out new Nike motto, my Nike slogan after one another, one another, one another once it's trained, because now it's repeatable and I can use it. That is learning and using generative AI the right way. Is anyone surprised, is anyone surprised that the, the ChatGPT version outperformed the human copywriter by that much? I am personally.

Jordan Wilson [00:23:23]:
I thought, if if I'm being honest, I thought it was gonna be head you know, kind of neck and neck between the the Nike, the human written ad copy, you break it, you own it, versus the kind of the prime prop polished version, which is legend legends don't chase records. They set them. Right? I thought it was gonna be, neck and neck, but apparently not. Alright. Let's get this let's keep this thing going. The second thing, if you ever hear this, if you ever see this, avoid avoid this person. Avoid avoid at all costs. Alright? Anyone that says ChatGPT is never out of date because of Bing.

Jordan Wilson [00:23:58]:
Right? That's not how ChatGPT works, y'all. Alright. So if you don't know, now if you are using the paid version of chatgptplus, which is gpt4, gpt4 turbo, you get essentially live access to Bing. Right? And so people think, oh, I'm not gonna get hallucinations because if I type something into chatgpt, right, its training data ends at April 2023, which is, which is now a year old. So people think, hey, if something's out of date, that's okay. I'm not gonna get lies or ambiguity out of ChatGPT because it's going to

Jordan Wilson [00:24:33]:
use browse with Bing. That's kind of

Jordan Wilson [00:24:35]:
true, but also very false. Alright. Let's talk about how this actually works. Here's the thing. Browse with Bing can actually read URLs. I see so many people sharing their prompts with with with screenshots. If you upload a URL into ChatGPT and say, hey, Bing, go look up this information. Right, and and and help me write this this better.

Jordan Wilson [00:24:57]:
Right? All Bing does is it looks at the words in the URL and it queries them. So you can't actually point Bing to a specific web page. Sometimes it'll work, and sometimes it'll go to the correct page. I've done this live on the show before. I've done 5 minute tutorials on this in YouTube. Y'all you have to pay attention. You have to know how a large language model works. Because Bing can't actually you can't direct Bing to a specific URL.

Jordan Wilson [00:25:24]:
It'll work sometimes, but it's just an SEO. It's an SEO game. And unfortunately, SEO is finicky. You can game it. Guess what? You know, if you want up to date information, let's say you you, you know, use Bing and you say, hey, Bing. I want, you know, a marketing plan for everyday AI. You know, use browse with Bing to find the most advanced tactics for multichannel marketing in 2024. So what it's gonna do is it's going to Bing, it's going to query multichannel marketing tactics 2024.

Jordan Wilson [00:25:55]:
Okay? So are we following? That's what it's gonna do. Guess what SEOs are great at? People who do SEO, they're great at gaming the system. Because there's a good chance, and I've done SEO y'all for 15, 20 years, someone probably had an article that from 2020 or 2021, and all they do is they update. They update the title. They update the URL, but everything else remains the same, and they game the system. So it might say top multi multi channel marketing strategies for 2024. Guess what? It might be from 2020, and maybe someone's gained the system. And Bing and Google don't know any better.

Jordan Wilson [00:26:34]:
They don't know any better. Alright. So you can't rely on Bing in that facet as well. Also, in this instance, right, browse with Bing may bring back outdated info from before the training data even. Right? So people think, oh, if it's after April 2023, I need to use Bing. You can't trust it. You can't trust a a a blind query because you don't know what's on the other end. Oh, Mike Mike felt personally called out by that one.

Jordan Wilson [00:27:05]:
But, hey, Mike's, an SEO specialist. He knows that's how that works. Right? It's not like an s e like, it's not like a dirty secret, but you can't necessarily trust a single source from a blind browse with Bing call. Alright. So if someone says, oh, use browse with Bing and chat JB team, you're fine. You'll you'll never have out of date information. It'll always be accurate. Not true.

Jordan Wilson [00:27:25]:
Not the case. Alright. Next. I'm gonna try to not spend too too long on this one. Yeah. It's getting it's getting hot in here, Mike. It's getting hot in here. Alright.

Jordan Wilson [00:27:35]:
So if someone says try these 20 prompts to 10 x your workflow or hey, here's, you know, 7 prompts that'll instantly double your business. Right? Or here's 30 prompts for, you know, marketing your startup. Right? That's not how chat j p t works. We kind of already touched on this with the Caitlin Clark example, but if you just start a new chat and you find some, you know, 19 year old who lives in the basement with his mom, who's who's now a an AI influencer. Right? And they say, use these 25 right? I gotta go back. How many how many, how many flames did we get? We got a lot of 3. Okay. We got a 2.

Jordan Wilson [00:28:20]:
Alright. So, it looks like people kinda want the heat. Alright. I'm gonna have to call this out. I agree with Brian. This is so annoying. Those prompts don't work. People sharing those prompts.

Jordan Wilson [00:28:31]:
Share them because they know they can trick you. Right? They want your email and then they're gonna sell you some crap in their newsletter. Alright? And they say, hey, you know, these 50 prompts, we spent so long making this prompt playbook to grow your business. Those prompts don't work. They are garbage. Garbage in, garbage out. If you go into ChatGPT, and this is literally what we teach and we show step by step in our free prime prompt polish course. Alright, in our PPP course.

Jordan Wilson [00:29:00]:
We take the highest rated, you know, prompt for a certain topic. We break it down. We dissect We talk about everything that goes wrong and then we teach you for free how to do it the right way. Y'all, copy and paste prompts is not how chat g p t works. ChatGPT is not deterministic. So if anyone's telling you, yes, these prompts will work for your business, that means they don't know what they're talking about. They have no clue. Let me give you a little hint here.

Jordan Wilson [00:29:24]:
Right? Let me give you a hint. If someone reaches out to you, and and they're like, oh, yes. I'm a I'm a prompting expert.

Jordan Wilson [00:29:35]:
Ask them questions. Be like, what are

Jordan Wilson [00:29:38]:
your thoughts on, you you know, 32, 32 shot chain of thought prompting versus 0 shot? Hey, explain to me the difference between, few shot and and chain of thought. Right? Like, say, explain your your prompt engineering methodology. Ask them. Right? Maybe maybe your company's hiring, you know, an outside expert to come in and and help your team with prompting. Ask them. Hey. What are your thoughts on MMLU benchmarking? Okay. Yo.

Jordan Wilson [00:30:14]:
I spent my weekend reading research papers about new prompting methodologies. That's what I do. You can't trust people. They're just trying to game you. They're trying to make you share their their crap. They're trying to make you sign up for their newsletter to sell you crap. It is crap. Sorry.

Jordan Wilson [00:30:32]:
Sorry for my pg 13 language. Right? Copy paste problems don't work. That's not how generative AI works. That's not how a trillion parameter large language model works. It is not deterministic. Those prompts aren't gonna get you anywhere. If you think prompts are gonna save your business, if you think they're gonna grow your your start up, if you think they're gonna help your company, simple copy and paste prompts. They're not.

Jordan Wilson [00:30:55]:
That is not how chat g p t works. Alright. Let's keep this one going. We got 1, I

Jordan Wilson [00:31:04]:
think we got one one more here. 1 or 2 more. Alright. So another one paste in your writing style and then chat g p t will write just like you. Guess what? That's not how chat g p t works. So here's here's the thing y'all. So many people think that this is how

Jordan Wilson [00:31:29]:
Chatcheapiki works. Right? Hey. Give it give it some examples of of of your writing style, of your brand voice, of your company voice. You know, just paste it in there. Give it an example. Then click enter, and all of a sudden it's gonna write like you. It's gonna write like your company. Right.

Jordan Wilson [00:31:43]:
You're not gonna need that copywriter. False. False. False. Okay. What most people don't know who aren't dorks like me and read, you know, hundreds of pages of research papers on advanced prompting methodologies and scientific research papers on prompt engineering. Most people don't understand. Large language models don't understand words.

Jordan Wilson [00:32:04]:
They don't. They tokenize. Right? They assign values. Right? So I'm I'm just showing an example for our livestream audience here. You know, I'm just gonna read, 2 sentences here. So it's it's talking about the word just and how the word just has different meanings. Alright. So as an example, it'll say, it'll be there just as soon as I finish this task.

Jordan Wilson [00:32:26]:
And then another usage of the word just. It's important to do what is just and fair in all situations. Right. So, So, essentially, the word just can mean a lot of different things. And this is a screenshot from OpenAI's tokenizer, which I encourage everyone if you wanna learn how large language models work, go use OpenAI's tokenizer. It's free in their playground, right, if you have an account. But what we're saying here is the word just. OpenAI has assigned, just in this I didn't mean to do that.

Jordan Wilson [00:32:54]:
Just in this use case, just in this small example, 4 different meanings or 4 different, contexts, you know, meanings to the word just because the word just can mean many different things. Right? So if you think you can just copy and paste a bunch of examples of your writing into chat gbt and get a brand voice or get this. Y'all, can anyone, and I'm sorry if this hits home and

Jordan Wilson [00:33:17]:
I'm sorry if this is you and I'm sorry if I'm calling you out, that's what we're here for. We're here to give people the truth. I'm

Jordan Wilson [00:33:25]:
tired of BS y'all. It's important that we all understand how generative AI works. I've been saying this for a long time. 20 24 things are gonna get bad. Things are gonna get bad. AI, layoffs, things are gonna get bad. I want you to succeed. You have to understand that's not how Chatgbt works.

Jordan Wilson [00:33:40]:
You can't just copy and paste a bunch of stuff and say do it like this. Because of the tokenization process, Chatgbt doesn't actually understand words. So if you can't give it enough examples to understand the word just as an example, it's not gonna work. You're still gonna get nonsense out. But why? Why are you still reposting all this nonsense, y'all? Why are you still supporting people that share bad information?

Jordan Wilson [00:34:07]:
Stop doing it. Learn to do it the

Jordan Wilson [00:34:08]:
right way. Here's an example. I actually gave a talk on this at one of the largest AI summits in New York City. This is what you have to do if you want to get a large language model to write like you. You. Right? Hey. Our podcast audience, you can't see this. But again, we have a lot of screenshots of very tiny text.

Jordan Wilson [00:34:25]:
Right? You have to turn unstructured data, which is content writing, right, into structured data. You have to create new rules for chat g p t so it can work within their rules. Right? Again, we teach companies this. If you wanna do it the right way, it's possible. But you don't just copy and paste a

Jordan Wilson [00:34:43]:
bunch of examples. You literally have to turn the art of copywriting into a science of rules for chat gbt to follow. Right? We call it our pattern recognition framework. It's not done the other way. If anyone's sharing that, they don't know what they're talking about. Sorry, not sorry.

Jordan Wilson [00:35:09]:
Alright. And then last last but not least, last but not least, if someone says this, run. Do not do not follow their advice. Do not listen to them. If someone says the free version of ChatGPT is good

Jordan Wilson [00:35:23]:
enough. Nope. That's not how ChatGPT works, y'all.

Jordan Wilson [00:35:29]:
The best analogy I can give, and I give this one all the time, the free version of ChatGPT is like a landline telephone. ChatGPT plus with gpt4 is like the newest smartphone. It's a huge difference. There's very little similarity between a landline and a smartphone. With a smartphone, you can run your entire business. You can you you can become productive in your personal and professional career. There's very few things you can't do with a smartphone. Well, it's kinda hard for me.

Jordan Wilson [00:36:01]:
I got fat fingers, y'all. But you probably get what I'm saying. The paid version of ChatGPT Plus because of its outside connections that you don't get on a free plan, you don't get that in the free version. GPTs. Poor plugins. They're gone now. Right? But GPTs, browse with Bing, code interpreter, DALL E. Right? All these things that turn chat g p t from a a copywriting assistant to a business operating system.

Jordan Wilson [00:36:29]:
Right? Being able to work with Zapier, bringing you know, being able to build your own g p t's and and kind of mini rag. Right? With with with your data. Being able to upload your data, and build a custom GPT. Right? All of these things you can't do in the free version. Or people that say, oh well, you know, I just get the GPT 4 via Microsoft Copilot. Okay. That's better than using the free version. But you don't have all those outside tools and being able to bring in your outside workflow.

Jordan Wilson [00:36:55]:
So if someone is telling you, oh, hey, your company, right, if you're hiring someone, if you're following someone on social media, if they say, hey, the free version is good enough, or hey, here's some free alternatives to chat ChatGPT. They're selling you snake oil. They don't know what they're talking about. That's like if someone were to really come up to you and say, hey, your company I see your company is using computers. Have you thought about this much more affordable version?

Jordan Wilson [00:37:24]:
It's it's called paper, a pen, and a landline. You should try it. Now shit. Here's here's my guide on how to save money in your business by using paper, pen, and a landline. Repost this and I'll send you the guide. Right? It's not how ChatGPT works. The free version, sorry. Garbage.

Jordan Wilson [00:37:45]:
Not good. You shouldn't use it. Paid version can change your business. If you really wanna grow, it can change your career. You can literally run an entire small business inside of ChatGPT if you know what you're doing.

Jordan Wilson [00:38:00]:
If you do it if you do it the correct way. If you understand prompt engineering 101, if you understand how to safely bring your data into ChatGPT, working with automation, I mean, having Zapier in there, being able to connect your own data. It is a business operating system. The free version is not worth your time.

Jordan Wilson [00:38:21]:
Is that too hot, y'all? Ugh. Sometimes I get

Jordan Wilson [00:38:24]:
done and I'm like, did I just offend someone? Right? Hey. Did I just offend Brian Brian Brian said this one the the last one is laughable. Right? Hopefully, I didn't offend you. Right? But there's so much bad information out there, y'all. I had to set the record straight. Because people who have no clue what they're talking about are trying to tell you how to run your business. They're trying to tell you how to use ChatChikiti to grow your career. Stop listening to them.

Jordan Wilson [00:38:53]:
They're selling you snake oil. I'd rather you figure it out now versus a year from now when it might be too late. Your company might already get passed up. Alright? If you're trying to implement generative AI, large language models into your company, which you should if you haven't already, You got an expiration date. Sorry. You have to understand large language models. You have to do the work. Yes.

Jordan Wilson [00:39:15]:
Generative AI can be a shortcut, but you gotta build it first. You gotta build the bridge, and that's hard work. We're lazy as humans sometimes. We want those copy and paste shortcuts. We want the the the the crap guide from the 19 year old kid, the 19 year old Billy Boy

Jordan Wilson [00:39:31]:
in his basement. We just want it to work. It's not gonna work. You gotta put the work in, but then generative AI will work for you. Alright?

Jordan Wilson [00:39:41]:
Let's do this. Let's do this. Let's see if we can properly let's see if we can properly give away, the GPU. Right? So I shoulda had the GPU ready to show me. It's literally behind me, here in my home office. So if you entered into our contest, all you had to do it's over now. All you had to do was was sign up. You got free access to the NVIDIA GTC conference, and then you were entered.

Jordan Wilson [00:40:09]:
So we had, I don't know, like a 150 people. Let's see

Jordan Wilson [00:40:12]:
if we can do this. So I entered every single person's name onto

Jordan Wilson [00:40:17]:
this list here. Don't worry. I'm not giving away your personal information. I I kind of, redacted everything, so we only have first name and last initial. Alright. Hopefully hopefully y'all can see this here. Let's see if we can give away this GPU. It's random.

Jordan Wilson [00:40:31]:
That's why I'm doing this. Hopefully, it works. If not, I gotta back up one. Alright. Ready. Click to spin.

Jordan Wilson [00:40:37]:
Here we go.

Jordan Wilson [00:40:43]:
Alright. We have right. Justin l. Alright. I'm gonna be sending you, some information, Justin, about this GPU. And also keep in mind

Jordan Wilson [00:41:01]:
oh, wait. There it is. Look at this. Just appeared appeared out of nowhere. Look at this.

Jordan Wilson [00:41:07]:
Alright. So, Justin, we're gonna be sending you this, this NVIDIA GeoForce RTX. Right? So you can also run, chat with RTX once you install that. Alright. Also, we're gonna be having we'll have more give, more giveaways. We'll be sending those to you. We also have some DLI credits to give away. Those will take a little longer because there's, like, 10 or 11.

Jordan Wilson [00:41:27]:
So, make sure to check your email, for that. Alright. I hope this was helpful, y'all. So make sure if you haven't already, repost this. If this show is helpful, please consider giving us a rating on Spotify, Apple, wherever you're listening to your podcast. Please share this with a friend. Right? Because here's what. Here's here's what you may not know.

Jordan Wilson [00:41:49]:
Someone in your life, a friend, a brother, a coworker, your sisters, neighbors, babysitters, dog walkers, best friend's boyfriends. Someone out there is getting bad advice when it comes to using generative AI, when it comes to leveraging large language models to grow your company, grow your career. Share this with them. Tag them in in in the post, repost this on LinkedIn. That would help. It would also help you to go to your everydayai.com. Sign up for that free daily newsletter. We're gonna be breaking today's episode down, going over more AI news, and a lot more.

Jordan Wilson [00:42:16]:
Thank you all for tuning in. We'll see you back tomorrow

Jordan Wilson [00:42:19]:
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