Ep 158: The ChatGPT Mistake You Don’t Know You’re Making

 

Episode Categories:

 

Resources

Join the discussion: Ask Jordan questions about ChatGPT

Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup

Connect with Jordan Wilson: LinkedIn Profile

Related Episodes

Overview

The latest episode of Everyday AI sheds light on the intricacies of leveraging ChatGPT and custom GPTs within business operations. Positioned as cutting-edge tools to facilitate language generation and understanding, these AI models offer tremendous potential for innovation, but also present unique challenges that business leaders must navigate to maximize their utility and mitigate associated risks.

Managing the Complexity of ChatGPT and Custom GPTs

Key insights from the podcast underscore the critical importance of managing the complexity inherent in using ChatGPT and custom GPTs. Business professionals must exercise caution when relying on these AI models, particularly in business contexts, and carefully assess their accuracy and reliability. The need for ongoing evaluation and customization to ensure optimal performance is emphasized, underscoring the significance of a meticulous and informed approach to utilizing these AI tools in business operations.

Strategies for Effective Utilization and Mitigating Risks

The podcast delves into actionable strategies for leveraging ChatGPT and custom GPTs while mitigating potential risks. Business owners and decision-makers are advised to implement conditional instructions and token counters, drawing attention to the necessity of managing memory issues and safeguarding the accuracy and relevance of outputs from these AI models. Additionally, the imperative of sharing insights about the challenges and solutions associated with ChatGPT and custom GPTs is underscored, reinforcing the value of a collaborative and informed approach when utilizing these AI tools within business settings.

Maximizing the Potential of ChatGPT and Custom GPTs for Business Growth

Despite the inherent challenges, the episode reaffirms the significant potential of ChatGPT and custom GPTs in driving business growth and innovation. By leveraging the power of these AI models with a nuanced understanding of their limitations and best practices, business professionals can enhance customer experiences, streamline operations, and drive strategic advancements within their organizations. The podcast's emphasis on providing daily insights and updates on ChatGPT and custom GPTs aligns with its commitment to empowering business leaders with the knowledge necessary to strategically leverage these technologies for sustainable growth.

Informed Decision-Making and Long-Term Vision

Given the rapidly evolving landscape of AI, the episode emphasizes the importance of informed decision-making when integrating ChatGPT and custom GPTs into business processes. By staying informed about the latest developments and best practices for utilizing these AI models, business leaders can proactively align their objectives with the transformative potential of AI, ensuring sustainable and value-driven application of ChatGPT and custom GPTs within their organizations.

Looking Ahead: The Future of AI Video Technology

The podcast episode serves as a valuable resource for business professionals on LinkedIn, providing nuanced insights into the utilization of ChatGPT and custom GPTs within business operations. By embracing a meticulous and informed approach to leveraging these AI models, business leaders can unlock their transformative potential while prudently managing associated risks. Everyday AI's dedication to offering daily insights and updates enables professionals to navigate the complexities of ChatGPT and custom GPTs, empowering them to make informed decisions that drive innovation and strategic growth within their organizations.


Topics Covered in This Episode

1. Impact of ChatGPT Mistakes
2. GPT Testing and Usage Issues
3. Caution When Using GPTs


Podcast Transcript

Jordan Wilson [00:00:17]:

There's a mistake that So many people so many people are making inside of chat gpt, and it's causing you to Get incorrect information, hallucinations. And if you're sharing these chats with others or maybe building custom GPTs, The people using those on the back end are running into these issues as well. I'm gonna tell you exactly what that chat GPT mistake is and how to correct it on today's episode of Everyday AI. What's going on y'all? My name is Jordan Wilson, and I am your host Of Everyday AI. We're a daily livestream podcast, free daily newsletter helping everyday people like you and me learn what's going on in the world of generative AI. Not just how we can learn it, but how we can leverage it to grow our companies and to grow our careers. If you're new here, thank you for joining us. Normally, I have a guest on, but, hey, every once in a while, I It's just me riding solo, and and and we dive in deep into, 1 issue, maybe 1 large language model you're using, a generative AI tool, something like that.

Jordan Wilson [00:01:22]:

And let me tell you what's a little bit different About everyday AI if you're new here or a reminder for, you you know, some of our some of our regulars, you you know, that are joining us, like Michael 4 gs saying good morning, like Tara Joining us from Nashville. Yes. This is a live stream. So if you're if you're listening on the podcast, always check the show notes. Come join us the next day. But this is an issue that is affecting so many people, and I don't think people know about it. So what's a little different about everyday AI is, hey. I'm a former journalist.

Jordan Wilson [00:01:50]:

So when a company says, you know, they release new features or when OpenAI says, hey. 128 k Tokens, context window for chat gbt, you know, giving chat gbt this massive memory. The first thing I do is I run and test that, and then I tell you all, like, hey. FYI. It's not 128 k. It's 32 k. Alright. So so so more on that big mistake, that people are making in a second.

Jordan Wilson [00:02:14]:

But first, As we always do, let's take a quick dive into the AI news. Alright. So a new report details concerns of Tesla's AI. So a former Tesla technician has blown the whistle on the company's AI technology used in their self driving cars, expressing concern about its safety and readiness for public use. So the technician leaked confidential Tesla data to a German newspaper revealing that thousands of customer complaints about the autopilot feature as well as corded accidents and safety concerns. Tesla CEO, Elon Musk, though, he's obviously defended the technology claiming that Tesla has the best Real world AI. Hey. If you're a Tesla driver out there, have you had issues before? I know friends with Teslas.

Jordan Wilson [00:03:00]:

I don't think they've ever had issues, but, reportedly, there's thousands of them. Alright. Speaking of things, controversy. So AI is already causing a stir in the 2024 presidential campaign scene, and we barely started. So according to a report from Forbes, Donald Trump recently claimed that the, the commercial from the group, The Lincoln Project, used AI to make him look bad in an ad that they ran against him. However, the ad, which was titled feeble, actually used real authentic footage of Trump, Highlighting some gaps and lowlights of his, presidential campaign according to this report. So, it's interesting because we know that, you know, as the 2024 elections here in the US, come and Roaring around. We we've been talking for a long time that, you you know, deep fake videos and misinformation and AI generated images are gonna be a problem, but I never thought about, you know, candidates saying, oh, you know, it when something bad happens saying, oh, that's AI.

Jordan Wilson [00:04:00]:

And it's like, oh, well, what if it's not? So, Maybe the 1st reported instance of that. Alright. Last but not least, 2 big tech titans are teaming up for an AI alliance, Meta and IBM. So, they've launched the AI, the AI Alliance, a group of leading organizations and industry startup, academia, research, and government To support open innovation in science and AI. It's it's not just Meta and IBM, but they're the headlining, names that are kind of launching this. But there's also 50 Founding members and collaborators from all kinds of big, research organizations, institutions, colleges, all all over the world. So, some some other big names, AMD, Cleveland Clinic, Cornell University, Dow, Hugging Face, So many others. Technically, my my alma mater, University of Illinois, is on there as well.

Jordan Wilson [00:04:50]:

So the objectives of the AI Alliance is to include developing A benchmark and evaluation standards fostering a vibrant AI hardware accelerator ecosystem in supporting global AI skills building and And exploratory research. So, pretty pretty interesting. I mean, a lot of heavy hitters coming together to form this alliance. You know, we haven't really seen this, at least Not here in the US, anything official like this, involving many different companies, many different, you you know, research organizations. So I I think that's actually a positive sign for AI when you have. Even if it's an unofficial, body, you you know, not they're not necessarily, there to govern, but, they are to make sure that AI is used more responsibly. So, I think it's good news if if you're a fan of generative AI. So, there's always more.

Jordan Wilson [00:05:36]:

There's always more news. So If you haven't already, please go to your everyday AI .com. Sign up for that free daily newsletter. We take every single day. We break down the podcast episode from that day. We always share if if we have a guest on the show, we always share a lot more resources that maybe they don't put out in the public, and and really just break things down Every single day, all the new tools and the trends and AI news, so make sure to check that out. So let's. Hello, everyone joining us.

Jordan Wilson [00:06:04]:

I I love I love going live. I I love being able to to learn together with you all, to to really just Break down different artificial intelligence systems step by step like chat, GPT, and others. So, good morning, Bridget. Joining us from Michigan. Todd, Man, our our Dallas contingent is really growing. Daryl, thanks for joining us from Philadelphia. Woozy says Woozy says he's from Kansas City, and his Tesla got him safe today with no issues. That's that's good to hear.

Jordan Wilson [00:06:34]:

Alright. So I wanna let's let's start with this. Let's start with this. What is The biggest chat GPT mistake that you've made. And maybe you've caught yourself or, you know, maybe someone else told you. And here's the thing. So much, especially recently, within ChatGPT has changed. So maybe you're listening to this podcast and, it's it's your 1st time here, and, maybe you're just a casual user of ChatGPT.

Jordan Wilson [00:07:06]:

I'm gonna give you the quickest history lesson ever. So Chat GPT has their free version and their paid version. The paid version Chat GPT plus is $20 a month. If you want that, you still can't sign up, there's a wait list. Essentially, they released a bunch of new updates about 3 weeks ago. Literally, their servers, which I think they have, like, every single and Piece of compute in the world still couldn't keep up. So you can't sign up for Chat GPT plus right now, but, in there, you have a couple different modes. Right? So you have, Chat GPT with plug ins, and you have, the default mode, which is actually really good now, whereas before I told people never to ever use it.

Jordan Wilson [00:07:44]:

But now the default mode, brings you a lot of new functionality. You can upload documents. You can use browse with Bing. You can use advanced data analysis. You can use DALL E all within the in The one default mode, so that's great. Then the other big new, kind of piece of of OpenAI's chat GPT since this dev day update, Which was announced November 7th, started to roll out to everyone the next week, is custom GPTs. So what's happened is Since there's been the ability to upload documents inside the default mode and now also with custom GPTs, and with custom GPTs, essentially, without diving into it too deeply, it allows you to kind of train your own version of chat GPT And to upload documents into its knowledge base, and then you can actually, share that with people. And ChatGPT said that they are going to be, Releasing their GPT store, I believe, in January or around, the beginning of 2024.

Jordan Wilson [00:08:40]:

So the the the same way that you saw, you know, kind of this explosion of the App Store. We're going to be seeing that with, kind of these these GPT store, or presumably, you will. Right? So It's essentially made the process between the the default mode, becoming now very easy to use and allowing you to upload documents, And also the the custom GPTs. So what we've seen, and this is indicative by, OpenAI really shutting down Their their process to upgrade users. What you've seen is is so many people, millions of people just flooding, chat GPT and building these things because now it's easier than ever before. It's easier than ever before to upload your own knowledge, To upload your own, company documents if you want to. Again, always read the privacy policy, and I'll say it as I always do. Never upload confidential or sensitive information into chat GPT, But it's now extremely easy that you you know, I wouldn't even say it's it's low code.

Jordan Wilson [00:09:40]:

It is no code. You you don't need to know really anything. And even the GPT, A process. It walks you through it. It's it's a guided process to set up this GPT. Right? So but what comes with that is now there's a lot of problems. Right. So I've been studying and watching, and I always like to look at people's tutorials.

Jordan Wilson [00:10:01]:

And a lot of people are saying, You know, Chat GPT, the quality has gone down recently. I don't know if any, if any of you on the live stream have have seen this, but people are comparing. They're saying, oh, GPT is getting all these things wrong that it used to get right a month ago. And, you know, I'm I'm I'm looking at all of these people reporting these issues and and, you know, trying to dig in to see Why? Why are they getting these issues? I'm not getting them. Our team's using chat gbt from, you know, morning to night uploading documents. We're never getting these issues. And what I've noticed is a lot of people don't actually understand the what it means to upload A document into chat GPT, and it's handled a little differently inside of the default mode versus if you're building a GPT a custom GPT. So here's the thing.

Jordan Wilson [00:10:50]:

I think a lot of people writing or complaining or trying to teach people about, You know, Chat GPTs are novices, but they claim to be experts. Right? I've never claimed to be an expert, FYI. But, you know, our team has been using the GPT technology since it was publicly available, and, I believe it was late I always forget late 20 late 20 yeah. Late 2020, early 2021. Right? So We've been using the technology for multiple years, and so many people just don't really understand how this works. So we're gonna dive in today, and we're gonna go over what I am now seeing as Probably the one biggest problem the biggest mistakes that people are making. And it's knowledge retention. Alright.

Jordan Wilson [00:11:32]:

Knowledge retention. Let's talk about what that means. Because there's there's technically 2 different things. So within chat GPT and all large language models, you have a memory. Right? And I'll be sharing about this at at one point, but we busted it down because During the, the dev day announcement on November 2nd, or no November 7th this year, Sam Altman said GPT 4 turbo is coming to chat GPT. Right? And what people, you know, ran and everyone got excited because GPT 4 turbo, their updated GPT 4 technology in Included a 128 k context window. So what that means is about 94,000 words, which is a lot before ChatGpT can start to, you know, Forget things or hallucinate. But it's not there.

Jordan Wilson [00:12:20]:

It's not there. Right? We're still actually at 32 k tokens, which is about 24,000 words. People don't know that. So that's that's that's 1 piece. That's more memory than knowledge retention, but that's important to talk about as well. Because in the end, the most important thing about using Chat GPT or any large language model is using it correctly. I tell people you have to play by Chat GPT's rules Or whatever large language model, you know, barge rules, in, anthropic cloud 2.1, whatever you're using. You have to play by their rules, but You also have to open up the read you you have to open up the rule book, and you have to Try the rules out for yourself.

Jordan Wilson [00:13:00]:

Right? That's a huge problem right now. Is there's there's a difference between marketing and real life use cases. Right? All the companies are which they should. Right? They should market their products and say, oh, they're the best. They do this. They do this. It's amazing. Right? But you go in and you test it, and you're like, no.

Jordan Wilson [00:13:15]:

There is no 128 k. It's 32 k. Right? So that's a huge issue, but let's talk specifically about knowledge retention. And, And, yes, I do wanna know from our from our, from our live audience if knowledge retention has been a problem for you. Or what is your other big chat gbt issue? Maybe I'll tackle them at the end. So, make sure if you're if you're like Connor joining us, live or Mike Lammers or, Brian Brian Bing, let me know what if if number 1, is Is knowledge retention a problem for you? Number 2, what is your biggest chat gbt issue? So let's look at why this matters and specifically What it means. Alright. So if you are joining us on the podcast, I'm gonna do my best to describe what I'm showing on my screen.

Jordan Wilson [00:14:02]:

But I think it should make sense. So in short, when you go into default mode, now you have the ability to upload a document, which is great. Because before, The only place you could do this was in advanced data analysis mode, which wasn't connected to the Internet. But now you can bring in a document, chat with it, and Through targeted browse with Bing searches, you can create content that is connected to the Internet, but also by using, A document to upload, whether it's, you know, your company's knowledge base, whatever it may be. So that's step 1 is you can upload a document. Great. Right? So we did this example. This is the document I uploaded.

Jordan Wilson [00:14:42]:

It's a PDF. I have a screenshot here. It's just Jordan writing samples. Right? So, but I hid something. This isn't a long document either. It's I I I think it was a 10 page document. So actually a very short document PDF. So I hid something in between, you know, toward the end.

Jordan Wilson [00:15:00]:

I said before we get started, here's some basic information about me. I said my name is Jordan. I'm from Chicago. I like the Chicago Bears, but they stink. Sorry. And then I said my favorite color is Carolina blue. Okay. So in theory, you think that once you upload this, it's there forever.

Jordan Wilson [00:15:24]:

And this default, chat GPT mode remembers that. That's obviously not the case. So we're gonna talk about we're gonna get a little bit into the details here, y'all, but there is a difference even between how The default mode in chat GPT handles uploaded documents versus how a custom GPT handles uploaded documents in the knowledge base. And there are some very and I've done hours of testing on this. Right? Putting on my own journalism hat. Never trust what a company tells you. You know? If if your mom says she loves you, get it in writing. Love you, mom.

Jordan Wilson [00:16:01]:

Thanks for, you know, listening to the show. My mom listens to the show. So you have to always pay attention and always Test this because let's see. Right? So now what I'm doing, I have a screenshot here, and I uploaded the document, And I'm just asking it to analyze the document. Right? So I'm not instantly asking it questions, you you know, from inside of chat gpt. That's not what I'm doing. I'm just saying, hey. Analyze my writing.

Jordan Wilson [00:16:31]:

Okay? So then I ask, what is my favorite color? And ChatGPT says, I'm sorry, but I cannot determine your favorite color. Okay? So I didn't do anything in between. We didn't run through that 32 k token, 24,000 word context window. So that's something that so many people are confused about. Right? Because they'll upload a document, and then they'll ask a question from it. Or maybe you're writing a blog post for your company, and you're uploading examples of, hey. These are the other webs web pages on our, on our website, and then you're telling ChatGPT to, you know, write this in your brand voice. If you are not making a call to ChatGPT To retrieve information, it may not.

Jordan Wilson [00:17:24]:

Right? And here's the thing. Chad GPT, y'all, it is the world's most advanced Autocomplete. That is all it is. Obviously, this autocomplete has 1,800,000,000,000 parameters in its big neural network brain, But regardless, it is an autocomplete. So I've I've built simultaneous chats to test this theory. And I could say, what is my favorite color? And chat 1 will say, I'm sorry, but I cannot Determine your favorite color, and chat too will get it correct even when I'm copying and pasting the exact same thing. So that's also important to know. You are never Going to get well, I won't say never, but you are very rarely going to get the exact same responses inside of ChatGPT because GPT 4 turbo is a large language model.

Jordan Wilson [00:18:03]:

This is essentially a smart autocomplete that thinks, acts, and speaks in tokens. Okay? So how do you fix this, And why is this a problem? Yeah, David. If your mom says you love you, get it in writing. Absolutely. So why is this a problem? Well, If you're uploading documents inside of default mode, you've you just think and you assume. Oh, great. Oh, great. I can spit out Content at scale.

Jordan Wilson [00:18:30]:

I can create a PowerPoint presentate. I can do anything because I've uploaded all these log documents that I took a lot of time to put together to give chat g p t access, but That's not how it works as you just saw. So the fix in default mode is actually extremely easy. All you have to do is call. You make a call. So what that means is at sometimes you need to point chat GPT in the right direction or tell it to reference something. Yes. It is always best to work with a large language model like a new employee that you're training and talk to it like a person, so you don't have to speak in fancy prompt to talk.

Jordan Wilson [00:19:07]:

But a lot of times, especially in this scenario when you're working in the default mode And you want to tap into knowledge from a document that you uploaded, number 1, you have to keep the memory in mind. So once you get past that memory, it doesn't matter what type of language you use. You're probably going to need to reupload that document once you get past chat GPT's memory limit. Right. Or all you have to do to fix it in default mode is to make the call. So what that means, I did the exact same thing. I just said using the attached document, what is my favorite color? And then you can see I screenshot it. And within chat gpt default, it'll always show you what it's working on.

Jordan Wilson [00:19:48]:

So if it is reading, quote, unquote, reading your knowledge base Or whatever doc or sorry. Not your knowledge base. If it's reading, the default mode is reading your uploaded document. It'll quickly flash up there, and it'll show you a little, Kind of like a little timer, and it'll say reading. You know, in this case, it says reading Jordan writing samples PDF. Okay? So now I know Because I called chat g p t to reference that document even though it was right there, and I only asked I only prompt 1 thing in between. It still may not know. Right? And here's the other thing.

Jordan Wilson [00:20:22]:

Even if you upload a document and you tell chat gpt, Hey. Retain all of this in your memory. Doesn't matter. Doesn't help. Tried it many, many times. Does not matter. If a lot of times peep what people don't understand, You either have to call to your knowledge source or you need to get it in the writing or in the in line text In order for chat GPT to best remember it, keep an eye on your tokens as well. Alright.

Jordan Wilson [00:20:49]:

So a little more Because GBTs can have issues too. Yes, people. I haven't seen anyone else on the Internet talk about this. So, you're welcome, 22 year old influencer who was an NFT crypto bro and now is an as well, and we've done plenty of double testing on this. Right? So what that means is doing the exact same prompt In a brand new chat, copy and pasting and making sure that it's not an anomaly to make sure that these are consistent issues, and they are. So let's look at how GPTs can have this issue as well. Okay. So, again, I was just doing some testing with, a custom GPT.

Jordan Wilson [00:21:44]:

I uploaded just 2 different docs. So a separate doc and then the same exact same writing samples doc. Okay. Super easy to configure. You know, you upload your doc, and it's kind of the same thing. So here's where you run into the issues with chat GPT in the custom GPT mode. But I also before you think about this, how you are using it, think. We are talking about an app store.

Jordan Wilson [00:22:17]:

Right? So presumably, people will be paying for GPTs. Right. And so this is also a shout out to all of you GPT developers that are gonna be selling something. Don't sell crap. Right. Take your time and build this the correct way. Because if you if you put this in your configuration, if you remind Your custom bot to every single time. Check the knowledge base regardless of the user in regardless of the user's query.

Jordan Wilson [00:22:51]:

It is much it's it doesn't get around that, issue a 100%, but it Decreases the likelihood that whoever is using this GPT, whether it's you or someone else, that they're going to run into this issue because here's why. You can actually confuse a GPT bot if it is not properly configured. Yes. I did it. Yes. This is what I do in my free time, y'all. I I bless bless my wife for having the patience with me as I, you know, play with chat GPT and plug ins at all hours of the day and the weekend. Right? But it's for you.

Jordan Wilson [00:23:26]:

It's for you guys, so I hope I hope you appreciate it. So you if you can you can trick Chat GPT. Not well, not even trick. But if someone is using your GPT, whether you're making it for a teammate, for yourself, If you put it on the GPT store, if your configuration instructions are not clear, it is very easy for your bot to either, hallucinate or sorry, your GPT To either hallucinate or not perform its most basic functions. Alright. So this GPT is essentially saying, hey. Write like Jordan. Right? So I have the, the the uploaded writing samples.

Jordan Wilson [00:24:05]:

So here's here's where it gets tricky. So right before, I didn't because there's a lot of this. I also tried to screw it up by putting in, about 200,000 words, Which caused it to break and no longer, you know, access the knowledge base, but that didn't happen consistently enough. But, essentially, what happened here is I uploaded my PDF. And then also right after that, I told chat gpt, hey. I'm eating M and M's Right now. And then later, I put in about, it was about 50,000, tokens. So I wanted to go past the 32 k limit.

Jordan Wilson [00:24:47]:

And then I said I I switched it up. I said, what am I eating, and What is my favorite color? Now let me break this down. The favorite color is in the document. Okay? What am I eating was in the inline text. Okay. And at that point, I was well past the 32 k token limit. Okay? So normally, on any question that you ask a GPT normally, It will almost always first browse through or screen the knowledge base. So what I found, And, you know, who knows? Maybe, OpenAI is aware of this and they're, you know, patching it up and making it more consistent.

Jordan Wilson [00:25:37]:

And, yes, you can get around this with better configuration instructions. But what I found is when you put a lot of unrelated, unrelated text. Right? I literally just copy and pasted transcripts from the podcast, Threw it in there between me entering this information about I'm eating peanut M and M's, put in all this information, and then I ask this very question, what am I eating and what is and favorite color. Because when I just say what is my favorite color, it gets it every time it reads the knowledge base. For whatever reason, When I ask an unrelated question to the knowledge base, it does not call to the knowledge base, which is problematic. Right. Because what it says here is it says I don't have the capability to know personal details such as what you are eating or what your favorite color is unless you tell me. My responses are based on the information provided in our conversation and cannot access personal data.

Jordan Wilson [00:26:33]:

Here's the thing. Obviously, it can. Right? Because when I asked the same question before all of that long text, it got it right. So for whatever reason, it could be a A context window issue. It could be the the the combination of asking something that was in line, but further than the 32 k back. But regardless, A very basic question from a very short document inside of the GPT's knowledge base Didn't work. Why does this matter to you and what can you do about it? Well, 1, you're gonna see the GPT store coming out, And you wanna make sure to only be, you know, buying things if if they are for sale. I'm sure there's gonna be free and paid ones.

Jordan Wilson [00:27:17]:

Right? You really wanna be buying things from people that know what they're doing. So it's almost a problem. Right? Think of 15, 20 years ago if you're looking at the Ios App Store. What if it was so easy for anyone to build an app and you were to trust or or run your company through it? You know, something a a a child made that has no clue how apps work or what an API even is. Right? So I love that it's so easy for anyone to go in there and build a custom GPT, but you have to keep this in mind. When the GPT store comes out And if you're using other people's GPTs, you really have to put them to the test. You have to run through all of these, different kind of scenarios that I'm walking you through right now. Because I think what so many people are doing with GPTs, which is great, It's they're they're uploading their company document.

Jordan Wilson [00:28:07]:

They're uploading their their writing samples. They're uploading whatever it is the project that they're working on. Right? And they're blindly trusting the process, which, again, if you're configuring this GPT on your own, Make sure to put instructions in there to every say, regardless of the user inquiry, always read through the entire knowledge base first, or, You know, you can have, conditional, conditional instructions. Right? So maybe instead of uploading, you know, one 50 page document. Maybe you upload 5, 10 page documents, and you give conditional instructions saying, you know, first, you know, 4. If they're asking about, you know, quarterly reports, look in the quarterly reports document. If they're asking about, you know, company services, look in company services document. Because, yes, right now, GPTs break pretty easily, especially when you're building them, but they also break, a little bit on the back end.

Jordan Wilson [00:29:02]:

But I know that that's something, that presumably OpenAI is spending a lot of time on right now because, I think the response to the GPTs has been overwhelming. That was a lot. Yes, Cecilia. So chat g p t is turning human. It skims and misses content. Kind of. Yes. Kind of.

Jordan Wilson [00:29:24]:

Yes. Doctor, doctor Matata, thank you for saying yeah. He said this is really great. Thanks for sharing. I do I do see a couple of questions. I'm gonna try to get to them. If you have any last minute questions, get them in now. So I'm actually hey.

Jordan Wilson [00:29:37]:

I don't know if if if anyone out there is listening in New York, but I will actually be speaking at the AI summit in New York. I'm actually hopping on a flight right after this, so I can't say for too long. But, hey, if you are gonna be out in New York at the AI summit, let me know. I'm gonna be giving a talk there on, guess what, how to make ChatGPT sound more human. Right? Because you can try to figure out on your own. You can Google it, but you're still just gonna find us. You're still gonna find me. So, let me try to get to a couple of these questions.

Jordan Wilson [00:30:08]:

Cecilia asking, is there a feature that tells you where you are in terms of token usage? Can you ask chat GPT to keep a running count of remaining tokens? So, Cecilia, great question. The best way to do that actually, I don't know if if most people know this. Chattopty is not great at advanced ad Computing, or advanced math. So I I always say use a token counter. Go check out our website or YouTube. We've we've done entire episodes on tokenization. We've done little 5 minute tutorials on, different Chrome extensions you can use that will count your tokens. But, yes, Whenever I use Chat GPT, I always have the token counter up because you need to know when it is running out of memory.

Jordan Wilson [00:30:48]:

That's extremely important. Let me see. Looks like 1 more question here. What's up, David? David said in a custom GPT, do you have to call back to info? Well, in theory, You don't. Because in almost most use cases, David, it will always check that knowledge base first. However, I recommend because of this same issue that I found and I'm talking about now and I haven't seen other people talking about it, you can confuse, a a GPT, a custom GPT, by putting in large amount of text or by asking it to recall something that was in line and And in the document at the same time after long text. I know that sounds like a very specific, kind of way to, encounter an error. But, Again, people are now running their businesses, which is great through these custom GPTs.

Jordan Wilson [00:31:42]:

So you need to be aware That it's it's not as cut and dry. It's not as cut and dry as you upload the document there once and it's safe. And, you know, you you can't just think, I'm gonna upload a 100 page document, and I'm gonna chat with this bot for, you know, every single day nonstop for a year and never run into issues. You should always be testing whether you're building it yourself or using someone else's. Do what I do. Hide something small in the middle or at the end of a document, Paste in, you know, 50,000 words and then ask about that one specific thing. So, David, that is what I would recommend doing. If you're using someone else's GBT, if you're building your own, yes, I would put in instructions to always, always, always go through The whatever knowledge base that you upload, however, the downside to that, if you have a lot of documents, or very long documents and if you put that into your configuration instructions.

Jordan Wilson [00:32:35]:

You are increasing the likelihood that the GPT is going to essentially, for lack of a better term, crap out. Right? You've seen those, you know, you get a little number at the bottom each time it makes an attempt. It's, you know, 1 of 1, 2 of 2, and, you know, I've seen people's screenshots where it's like 37 of 37. So, the more resources that you require your GPT to go through, the more likely it is at At least now while OpenAI is tackling, kind of this, resource issue, the more likely it is to not give you a positive return. So You do you may at times depending on, you know, your documents that you have, depending on your documents that you have in there, depending on how, they're set up, you may have to go back and forth, between, speed and, truth. Right? Obviously, you always wanna side on the error of truth, but, Yeah. It it it might mean just, you know, breaking up a very large document into smaller documents and then having, configuration instructions inside of chat GPTs Telling it to look in specific documents for specific queries. But if you're not running into the issue and if you're getting consistent outputs every single time, you're all good.

Jordan Wilson [00:33:45]:

Alright. Brilliant show, Jay. Wow. Thanks, Jay. I appreciate that. So, Hey. If you feel like Jay, if you're listening on the podcast, if this was helpful, if you're getting value out of the Everyday AI Show, do me a favor. If you aren't already subscribed to us on Spotify, Apple, please do that, and give us a rating as well.

Jordan Wilson [00:34:07]:

But share this Share this with a friend. If you're listening on the podcast, click that send button. Send this to a friend that you know is using chat GPT or building GPTs. If you're listening live, share this post on LinkedIn. Tag someone in the comments on, you know, someone that you think needs to hear this. You know, sometimes people ask, hey, Jordan. You've provided so, you you know, so much great information for for me and my company. What can I do? There it is.

Jordan Wilson [00:34:33]:

Share this. Hit that repost button. Tag some people in your network. Try to help more people make fewer mistakes inside of chat g p t. So Thank you all. I hope this was helpful. Make sure to go to your everyday AI .com. Sign up for that free daily newsletter.

Jordan Wilson [00:34:49]:

Join us tomorrow. Join us tomorrow as well because we are bringing on a leader from Microsoft to talk about how copilot can help you build Your, leadership, but also it can help you learn better. So I'm extremely excited to talk about Microsoft Copilot. So hope to see you tomorrow and every day on EverydayAI. Thanks!

Gain Extra Insights With Our Newsletter

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