Everyday AI Podcast – An AI and ChatGPT Podcast - EP 39: How To Keep ChatGPT From Lying

Episode Date: June 16, 2023

What do you do when ChatGPT keeps lying? That's referred to as ChatGPT "hallucinating." Today we're breaking down how to make sure you're always getting up-to-date and factual information from ChatGPT. For more details head to our episode page!Time Stamps:Full show notes here[00:01:15] Oracle stock rises after announcement of generative AI[00:02:12] AI is coming to Starbucks[00:03:15] Are AI watermarks coming to social media campaigns?[00:04:46] What are ChatGPT Hallucinations?[00:09:35] 5 Ways to Avoid ChatGPT Hallucinations          [00:09:40] 1. Using the Wrong Version          [00:11:32] 2. Using the Wrong Mode          [00:13:32] 3. Bad at Prompting          [00:15:57] 4. Not Specific Enough          [00:17:28] 5. Not Feeding ChatGPT Data[00:19:55] Audience Questions about ChatGPTTopics Covered in This Episode:1. Large Language Models and Hallucinations- Discussion on the potential for large language models to provide inaccurate or false responses- Focus on Chat GPT2. Recent AI-Related News Stories - Oracle's entry into the generative AI space - Starbucks' implementation of AI chatbots at their drive-thrus- Ogilvy's push for advertisers to disclose their use of generative AI3. 5 Tips to Avoid Chat GTP from Providing Hallucinations - Keywords and its context - Information input - Shorter text - Fine-tuning - Avoiding keyphrases and unlimited textKeywords:Everyday AI, language models, Chat GPT, inaccurate, false responses, AI-related news, Oracle, generative AI, Starbucks, AI chatbots, drive-thrus, Ogilvy, advertisers, campaigns, five tips, avoiding hallucinations, false responses, podcast, speaker, thank you, joining, subscribe, rating, daily newsletter, sign up, motivational message, break barriers, next episode.Send Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info) Start Here ▶️Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com Also, here's a link to the entire series on a Spotify playlist. 

This is the Everyday AI Show, the Everyday Podcast where we simplify AI and bring its power to your fingertips. Listen daily for practical advice to boost your career, business, and everyday life. Meet Firefly AI Assistant, now live in Adobe Firefly, the All In One Creative AI Studio. Just describe what you want to create and the assistant handles the rest, orchestrating multi-step workflows across Photoshop, Premiere Express, and more in one conversational interface. You direct the outcome. The assistant accelerates execution. Is your chat GPT lying to you?

That's called a hallucination. And chances are if you've used chat GPT, you might have experienced this. So we're going to talk about how to keep chat GPT from lying to you today and a lot more on everyday AI. So this is your daily live stream podcast and newsletter to help everyday people like you and me not just get the most out of AI, but to actually understand what's going on and how we can use it

in our everyday lives. So before we start talking about chat GPT and why it's hallucinating, let's go over what's happening in the AI world today. A lot of interesting news and I think some important news. So as a reminder, if you are listening to us live live, please leave me a comment. This is just me today. I can talk by myself all day. But I'm I'd rather answer your questions. So if you are tuning in, please leave a comment and let's get into the news. So Oracle, their stock is rising after announcing earlier this week that they're getting into the generative AI game. So generative AI obviously is, you know, text to something, you know, large language models, text to image, text to video, all that stuff.

So Oracle announced earlier this week that they were teaming up with Cohere. and their stock has soared. So Oracle is obviously the world's largest database management company and up 20% in the days since announcing this new generative AI offering. So it's crazy to see these big companies because also Oracle has continued to lay off employees, hundreds of employees, but their stock is rising at an all-time high, specifically after announcing this generative AI piece. We already have some comments in today.

This is great. I'm going to get to these in a second, but let's get back to the news. So Starbucks, this one's good. Starbucks AI is coming to a Starbucks near you. So they just announced, this is fresh, just was announced like an hour ago, not even. So they are getting into the AI chatbot game. So coming to a drive-thru near you, you may or may not be talking to a large language model soon. So I think it's important to remember.

Remember, I'm going to get my take on this. We've all probably experienced these automated drive-thrus years ago, right? So they've been testing this, but that was before large language models got as powerful as they are now. So I think we all probably had an experience at some point, especially if you live in a major city here in the U.S. Years ago, they started to roll these out. But I think they're actually going to start to get good. So Starbucks just announced that. It should be interesting to see how that rollout goes, and that's fresh piping hot news.

It's hotter than my cup of coffee here. That's no longer hot. Third story that I want to talk about today, another recent announcement. So are AI watermarks going to be coming to social media campaigns? So Ogilvy is one of the largest social media agencies in the world. And they actually just recently announced in our pushing. all advertisers to disclose when they use generative AI in social media campaigns. So you may not know this, but a lot of agencies, you know,

and agencies are sometimes working with hundreds or thousands of different clients who are taking out ads. And a lot of people are using generative AI models in their ad campaigns, right? So Ogilvy is leading the push to make a tag that this is AI generated and to disclose. Will it happen? I don't think so. Why? Money.

As soon as you start disclosing that something is AI, those brands start to lose what they feel is genuine credibility. So yeah, brands are creating. I think pseudo relationships with their end customers because they are using generative AI and, you know, not real people. So I don't think that this will stick on. I love that Ogilvy's doing this and that they're pushing for it. I do think it's needed.

In the end, money talks louder than regulation. That's, there's no way around that. Money talks louder than regulation. So it'll be interesting to see. So let's talk hallucination. So if you are tuning in live, please give me an example. Has dropped me a comment? Has hallucination happened to you before?

So let's talk. But first, a couple comments already coming in. Harvey saying great to be here. Harvey gave a fantastic talk yesterday at the AI summit, a pretty large online summit. Harvey was amazing. Make sure to check him out. I'll probably throw a comment in here.

Ryan is driving and listening. Ryan, be safe while driving, but thanks for joining us. All right. So let's get into it. Let's talk hallucinations. All right. So what is? a hallucination. So what we really have to do before we even jump into what a hallucination is,

is we have to understand what a large language model is. So chat GPT is a large language model. So without getting into the specifics, think of it like this. We've all probably used Google. And you start to type in a Google search and you'll see auto correct. And it might suggest five, six, seven different things. A large language model when you start to type something or if you ask something instead of five or six or seven, think five, six, seven billion different combinations of things. So that's what a large language model is. It is essentially a level of auto-complete that it is hard.

to fathom because of the size of these large language models and all of the parameters that there are. Another thing to keep in mind before we jump into hallucinations is, what is a model? It is that, right? It's all based everything that you get from chat GPT or if you're using Google Bard, Microsoft Bing Chat, Anthropics Cloud, which we don't talk about on the show enough. Whatever text generating model that you're using, that's all it is. It's a model.

So that's why you are probably getting hallucinations, all right? So before I give you five tips on how to avoid hallucinations, I'm going to go ahead and tell you this. I've been using the GPT technology since 2020. So most people got introduced to chat GPT or the GPT technology. when chat GPT came out in, that was I think late November of 2022. So it's been out for about eight months now. I've been using it since 2020. So the GPT technology, OpenAI, made that available to a lot of third-party companies. So we've had a lot of experience. Our team has a lot of experience using this technology before chat GPT came out. So I did get, you know, personally,

some hallucinations or some lies early on, but probably in the last five months, I haven't gotten any hallucinations because you have to understand how first you have to do what's on the screen here is you have to understand that chat GPT is a large language model. Okay. And then you have to use it correctly. So I'm going to give you five tips. But before I do, let me just, we have a couple comments coming in. I want to make sure to talk about this. So Dr. Harvey Castro is saying The scary part is the reference and article did match at all for the comment. Yes. Adobe just introduced an entirely new way to create,

bringing the power and precision of its creative suite into one conversational experience. Meet Firefly AI Assistant, now live in the Adobe Firefly app, the All In One Creative AI Studio. Powered by Adobe's Creative Agent, Firefly AI Assistant lets you start with your vision, just describe what you want, and shape the outcome as it takes. makes form with the assistant. The assistant orchestrates multi-step workflows, drawing on 60-plus pro-grade tools across Adobe Creative Cloud apps, including Photoshop, Illustrator, Premier, Lightroom Express, and more to help bring your ideas to life. You can also get started with creative

skills, a growing library of pre-built workflows for common creative tasks, like batch editing photos, creating mood boards, portrait retouching, and creating social variations. Every step the assistant takes is visible so you can refine, redirect, or take over at any time. You stay in the driver's seat as the creative director. Adobe Firefly AI assistant now in public beta. See it today at Firefly.adobie.com. Hallucinations, if you're not using chat GPT correctly, they can spit out the craziest things. And obviously, you know, Samsung has unfortunately been on the news.

You know, there's the case where the lawyer in New York submitted fall. documents to a court because ChatGPT hallucinated in what this lawyer used in a court filing and made up fake cases and they submitted it, right? That's a hallucination. Not good. So another comment here saying I use ChatGPT to generate Python web app ideas, 6040 at providing good code. Yeah, same thing. So that's a great point.

So it's a magial. So it's not just text or paragraphs or content. It can be code as well. It can be math. You're going to get, if you're not using chat GPT correctly, you're going to get hallucinations. It's going to lie to you. All right. So without further ado, let's talk about those five, the five ways you can stop getting hallucinations.

Number one is you're just using the wrong version. Okay. So if you're listening to this on the podcast, I have some slides up on my screen, but they're not. They're not terribly in depth. It's more just people have something else to look at aside from my face for those that are joining us live. So all I'm talking about here using the wrong version is if you're using the free version of chat GPT, you're going to be getting more hallucinations than if you're using the paid version. That's just because the paid version, GPT4, is immense.

intensely more powerful. You know, I actually, a funny story, I was helping a family member with a project. And this person was using the free version, GPT 3.5. And I said, how can you do this? You know, I use chat GPT hours every day. And using the free version, not only are you subjecting yourself to more hallucinations, but also the redundancies are out of control. The quality is low.

So you're using the wrong version. I'm not paid. I'm not a paid spokesperson. But if you're using the free version of chat chipt, you're doing this all wrong. It's $20 a month to get the paid version. Think of what your time is worth. And you will save literally hours in the first 30 minutes that you use the pro version correctly. Okay.

So that's number one. You're using the wrong version. As a reminder, if you are tuning in live, thank you for the comments so far. But keep them coming because I want to help you guys through this. That's what everyday AI is about. It's helping everyday people understand and use AI. So if you do have a question about something that's on screen or something just about hallucinations, make sure to drop it.

So the second thing or the second reason why you're getting hallucinations from chat GPT is you're using the wrong mode. Okay? That's very important. And we're going to get into that more here in the show. So what's that mean? So in the paid version, there's different modes. So GPT4 has different modes.

If you start a new chat, even if you click GPT4, you may not realize this, but it always defaults to default. So the different modes in chat GPT4, there's actually four. I only have three. So I know no one from chat or no one from OpenAI is probably listening to the show. But if so, can I please get the code interpreter already? But the four different modes are default. That's number one.

Number two is to browse with Bing, which is essentially web access. The third one is plugins. And I think the last time I checked, there's 400 plus third-party plugins that can extend the functionality of chat GPT4. And then the one I don't have access to yet is the code interpreter, which helps you interpret code. Pretty straightforward. You know, Christopher with a comment, I agree the difference between the free version and the paid

version. There is a huge difference between 3.5 and 4. Chris, that's a great point. I'm going to go ahead and shout out Chris as well because Chris, we still have to announce the giveaway winner, which we'll do next week. But Chris actually won the chat GPT giveaway for us for the most referrals. So shout out, Chris. You did an amazing job referring people to everyday AI. But we still are going to be giving away the one more, one year license for a random person. So we're giving away to Chris 1-1. So thanks for the comment, Chris. Pierre Paul, he only has two. He's missing out on the plugins in the betas. Yeah, oh, man, yeah, you got to get the plugins. All right. So let's keep going on.

So we said number one is you're using the wrong version. Number two is you're using the wrong mode in the in the version. Number three, you're bad at prompting. I'm sorry, you're bad at prompting. Rob, Rob, shout up. Thanks for joining us. I'm going to leave a comment in this later. If you aren't following Rob on TikTok, you need to be following Rob on TikTok, giving out great advice to job seekers. So problem number three is you're bad at prompting, okay? And here's the problem. Social media is the problem of prompting, period.

I have a fake tweet on the screen from every tweet ever saying, you know, 20 powerful chat GPT prompts to save you 20 hours a week. If you go on any social media, especially Twitter and LinkedIn, you're probably going to be seeing these every day. This is a problem with AI in general, specifically chat GPT, because you see these, you know, influencers and these, you know, kind of strong voices in AI saying, this is all you need. And so what happens? These are kind of what's referred to as super prompts. So, you know, there may be a prompt that's, you know, 20 to 50 words long. And they're like, oh, it's going to give you great, great results. It's not.

It's bad. In most cases, those super prompts can still hallucinate. You can use this great prompt that's supposed to save you 20 hours a week, and it can still lie to you if you use it exactly how they're saying, I'm not an advocate if you couldn't tell of using these super prompts that you see online because they're not good, period. Another question coming in, is this the case if you use the API, which is not free? Sorry, Madgell, I think I caught your question a little too late. If you explain it a little more, I think I can probably answer that.

So the number three reason that your GPT is hallucinating is your bat at prompting. So we actually do this. We do a free course. It's called Prime Prompt Polish. Maybe leave me a comment if you're listening. If you've done the course, maybe just drop me a comment. Let me know or let the people know if it's any good. I think it's good.

Like I said, it's a free course. We've been using the GPT technology since 2020. So I feel that we're pretty good at getting the most out of GPT. And like I said, I haven't personally had a hallucination from GPT in months. So let's go to number four. Looks like our little sub had got messed up there, but that's fine. So you're not specific enough. And this goes to prompting.

Because what you probably can't see there behind is talking about priming. There's a whole step that people aren't doing in chat GPT, which is the priming phase. So normally, even if you're using one of these super prompts, it's saying like, oh, act as a expert copywriter. And here is some background. And then here is a specific prompt. Even if you do it that way, you're going to get terrible results and probably some hallucinations, period. So you need to be priming, okay? So before you even give a prompt, you need to tell chat GPT of its role with specific

examples. You need to get background of who you are. You need to get background of your audience, of your USP, of their pain points. And then you also need to ask questions of chat GPT before you prompt it. Say, what other information do you need to know? So I know that sounds like a lot of work, but hallucinations are a problem, right? anyone or just crazy redundancies or or just information getting information back from chat gpte that is not useful um so that's that's happening a lot so the fourth reason is you are not specific

enough you need to go through multiple steps before you even prompt chat gpt for information you need to prime all right so let's go on to the last reason why you are probably still getting from chat GPT. So you're not feeding GPT data. So you're probably saying, Jordan, if I'm using the paid version of chat GPT and I have browsing mode activated or I have plugins,

chat GPT should just know everything, right? Yeah, wrong. Because here's the thing. Unless you are very specific in your prompt, which most people, aren't, right? Unless you're very specific, there's still billions of web pages on the internet, right? So even if chat GPT has web browsing mode, and maybe you have a small company, or maybe you work at a Fortune 500 company and you're working on something about an annual

report, right, that exists on the internet if you're filing it, right? So instead of just assuming that chat GPT knows where to look. Sometimes you need to feed chat GPD data. So in that priming process that I talked about and, you know, talking about giving specific information before you even prompt, I will often, if I have web browsing enabled, I will, when giving background, I can say more background can be found here for this piece of information. I'm giving chat GPT.

And I will leave a link and then chat GPT, even if it's a long web page, it will go and quickly become an expert in that web page. Another great thing, which we're going to feature in the newsletter today, is uploading PDFs to chat GPT when you're priming it. So you have to be giving chat GPT data in a lot of cases to avoid hallucinations. So those are the five reasons that you're not getting accurate information from chat GPT. The five reasons or the five ways that you can stop to get hallucinations. All right. So I'm going to go through them all very quickly now to recap.

Let's go. Number one, you're using the wrong version. Number two, you're using the wrong mode. Number three, you're bad at prompting. Number four, you're not specific enough. And number five, you're not feeding chat GPT data. All right. So thank you for joining me.

I do have a couple of questions. I'm going to go ahead and take here before we wrap up the show. But as a reminder, if you're still listening right now, whether live or on the podcast, this is every day this live stream is in a LinkedIn thread. So if you're watching now, just type in PPP. Go ahead. I'm going to send you information about our free course. So you can stop getting hallucinations from chat GPT.

It's a free course. We don't sell anything at the end. We just like helping people. So let me get to these questions. So let's see. Madgill is asking about the difference between 3.5 and 4 for the API. And is the API 3.5 bad in the free version? It's a highly technical question.

I'll say this. In my experience, anyways, very everyday people have access to the 4.0 version of the API. As an example, I applied for API access as an individual. I think within three days of when it opened up. And I still don't have four. So even if you, this is very important, a little technical, but even if you have the pro version of chat GPT, GPT4, you probably don't have the GPT4 API version. Usually they're only rolling those out to, you know, people that have, are using the API

and have hundreds of or thousands of paying customers. So most people don't have that. version. So you're going to need to go to the OpenAAI Playground and click on the options. And most people don't have the API, the version for unless you have a service that you're providing and you have paying clients. Oh, cool. We got some people that are dropping in the PPP. Awesome. So PARVs, shout out Parves. Follow PARVs on LinkedIn, too. He's putting out great things about AI. So thank you. I'll send all the information to all of you as well. A couple other questions. So, um, okay, Chris, Chris actually shouting out the GPT course.

Thank you. He says, uh, I highly recommend the PPP course because you will definitely learn a lot of new information. That's actually helpful. Thank you, Chris. Harvey with another comment, the million dollar question, did chat GPT help you come up with the top five? Um, no. I know, crazy, right? Chat GPT is not great at coming up with its own problems or poking holes in its own armor. I've tried it before. It's not good. But yes, Harvey, I appreciate that question. Chat GPT did not help in the making of this podcast. This is even this, you know, C-minus graphic design that you see here. That was all me. So Monica, Monica asked, If you upload PDFs to chat GPT, will that information become public?

Oh my gosh, great question. The answer is yes. So the answer is yes. So that's a fantastic question. And this is, you know, when I referenced the Samsung incident earlier, I should go into a little bit more depth. So an employee at Samsung, I believe essentially uploaded some proprietary code into chat GBT to help work with the code.

So not good. So, yeah, a lot of companies are saying, be careful when using chat GPD or other large language models like Bard, because yes, when you are uploading information, whether it's text space or PDFs, in theory, OpenAI does then have access to use that information to train its models. So will it become public? That's a tricky question. It's not like if I upload a PDF or if I load information about my company that any of you will be able to see it. But as far as I know, and if someone in here knows more, please,

please correct me in the comments. But if you do upload any text, any PDFs, yes, ChatGPT has, or sorry, OpenAI has access to that and they will use that to help train and refine their model. But it's not like when you do that, that information doesn't become public for anyone else per se, but it is being used by chat GPT, by OpenAI to better train their models. So Monica, fantastic question. It's something we talk about. So there is, on Monica's point, there is a way to keep all of that private. So there is a way in chat GPT to, I'm going to see if I can, if I can multitask here

and also share my screen. So give me a second. So yes, there is a way to keep. everything private. So let me go ahead and share my screen here. So give me a second. And I'll show you how to do this. So if you go into your settings in chat GPT and go to data controls,

you can go to this chat history and training and you can turn it off. At that point, your information is not being sent back to chat GPT to improve the model. However, the huge downside. is the history is not saved, right? So as soon as you close out, everything you worked on is gone. So yes, you can technically keep all of that information from being sent to open AI to improve their future models. But you are then at that point losing the ability to save it.

So Monica, I hope that answered the question. Let me see. I don't think, yes, yes, like what Harvey said there. Thank you. Harvey also asked the question. answer the question. He said you can change your setting so that the information does not use to train your data. But yes, the obvious downside is then your chat is not saved. So if you're really putting a lot of work into your individual chats and building what's called expert chats,

that's what we teach people to do, you can't do that. So you can't retain it. And after you go through the process and you create a great chat that's spitting out great outputs, if you toggle that setting off, you can't go back. So that's the downside. So as a reminder, I see some PPPs. in the comment. I'm going to send you guys some information. Harvey, thank you for the compliment saying great talk. Appreciate it. So yes, if this was helpful, if you are still getting hallucinations, type in PPP. I will send you this. But as a reminder, this is all for hallucinations. I don't want to keep this going for, you know, three hours, you know, but go to your everyday AI.com. We have a daily newsletter. It's free guys. There's plenty of daily newsletters out there. Maybe I'm biased. I think we're doing a

fantastic job to help the everyday person. That's the thing. A lot of resources out there for AI news and just to keep up with AI. They're for very technical people and it's hard to keep up. So we, for the everyday person, we have a free newsletter, your everyday AI.com, sign up for that newsletter. We're going to be doing a little tutorial today on how to even what Monica was saying. uploading a PDF and being able to use that information in your chat GPT, fewer hallucinations. So thank you all for joining. And we'll see you on the next show of Everyday AI. Thank you.

Meet Firefly AI Assistant. Now live in Adobe Firefly, the Allman One Creative AI Studio. Just describe what you want to create in your own words and the assistant handles the rest, orchestrating multi-step workflows across Adobe Creative Cloud apps, including Photoshop, Premiere Express, and more. in one conversational interface. You direct the outcome while the assistant accelerates execution. Stand control with the ability to step in and refine at any time.

See it today at firefly.adobie.com. And that's a wrap for today's edition of Everyday AI. Thanks for joining us. If you enjoyed this episode, please subscribe and leave us a rating. It helps keep us going. For a little more AI magic, visit Your EverydayAI.com and sign up to our daily newsletter so you don't get left behind. Go break some barriers and we'll see you next time.