Loading summary
Transcript3 lines
- [00:00]
A
If you're not using Ironclad for contracts, you could be leaving millions on the table without knowing it. Every contract holds renewal dates, pricing terms, and obligations you can't afford to miss. But good luck finding them when it matters. Ironclad's AI instantly surfaces what matters so you can act before opportunities slip away. That's why they're trusted by OpenAI, L' Oreal, and Salesforce. Find the savings hiding in your contracts@ironcladapp.com podcast that's ironcladapp.com podcast.
- [00:33]
B
Hey there. Welcome to the ChatGPT experiment. This is the podcast designed to help you better understand how to use tools like Chat GPT to gain a nugget to help you in your personal or professional needs. My name is Kerry Weston. I am your host. How you doing? No music this week as I'm stuck on the road and don't have my usual files, but I did want to get an episode out and to you. Normally I would be in Bangor, Maine recording this, but today I am in Atlanta. I am still in Atlanta because much like many people on the east coast, my travel schedule got disrupted by the snow and the ice. The good thing is there's no airport time. I just simply had flights going home canceled. So here I am. Did you guys get caught in it to get a bunch of snow? I checked in home. There was about 14 inches of snow that came in. The unfortunate part about it, as I'm learning, is it wasn't snowman snow. It was light and fluffy, easy to shovel, but not a lot of stick to itiveness in terms of the ability to make snowmen, snowballs and sticky stuff. So I am down in Atlanta. I did a presentation down here for a transportation and logistics conference in the trucking industry. We did a couple sessions on Chat GPT and it's always interesting to me when I meet people in different industries and with different needs and different perspectives on technology, how similar the questions and how similar the needs and the positions and the awareness of ChatGPT and tools like it come out. So I thought today I would just start with a simple nugget that resonates to many people. Two most important things, I think no matter what you're doing with ChatGPT or how comfortable you are with ChatGPT or tools like it that I think is worth repeating. And the first one is talk to it. I just keep coming back to that phrase, talk to it. And remarkably, the ability to have a two way conversation with a tool like ChatGPT is still foreign to Many people. So I'm going to ask you, do you think you talk with ChatGPT or are you talking to it? Are you treating it like Alexa and like Siri and like a verbal version of Google, or are you literally having a conversation with it? And I think it's that two way conversation that really, I know it surprises people, it opens people's eyes and it allows people to see what's potentially there for them. Right. And that's the second thing that I want to share, is just simply asking it how it can help you in a meaningful way. Just sharing with it who you are and what you can do with ChatGPT is a pretty eye opening experience for many as well. And when I say that, I mean literally talk to ChatGPT by saying this is who I am and this is what I do. And I've heard that you're helpful, but I don't know anything about you and how do you think you could help me? And it'll come back and it'll tell you. So I think talking to it still foreign to many and asking it for that one thing, just finding that one thing that can make ChatGPT incredible, helpful. Whether it tells you, here's another way of looking at it. Whether it tells you that based on what you're sharing with me, here's how I can be helpful. The other thing you can do is just do an inventory of your day, personally or professionally. What is one thing that you use the computer for that takes up some of your repetitive time, your busy work, what is that one thing? Now when you come up with that one thing, you don't need to model out how ChatGPT is going to help you. You don't need to have a timeline or a plan or a blueprint or any of that stuff. You can literally go to Chat GPT and say, hey, I do this one thing. It takes a lot of time. This is why I do it. It's important to my job, or maybe it's important to my hobby or whatever it might be, and I'd like to spend less time doing it because it's busy work. How do you think you can help me? And just that question, how do you think you can help me? Will open up a remarkable conversation because it'll start thinking about your position. In fact, if we go back to the four part framework that I share all the time, four part being telling it, what are you doing? Why are you doing it? What does success look like? Give it a guide, right? And then say, do you have any Questions for me, that four part framework, which is spelled out in a previous episode, the ability for you to give it more context, thinking of it as your amazing intern and just sharing with it something that occupies your time, something that takes up space in your day and saying, how can you help me? So I think the two things, the simplest two things that still have the most impact and the majority of the conversations that I have with people when I'm coaching and showing and guiding is just talk to it and find that one thing. Because once you can become comfortable with that one thing, your ability to see how else it can be helpful is easier because you're already used to talking to it. You're already used to not having the answers. You're already used to not seeing the end, but having a conversation at the beginning and being vulnerable and saying, I'm sure you can help me, but I don't know how will churn ChatGPT into that problem solving, conversationalist tool that gives terrific value, right? So I spent two hours in a couple workshops yesterday down here in the conference. And when I polled a group, I usually start my sessions by asking, how comfortable, right? Usually there's three Cs that I find in people. The capacity, the capability, Right? The capability and capacity to learn. Do they have it? And the second thing is the curiosity. Are they interested? So if they have the capacity to learn and if they have the curiosity, usually ask them how confident they are. And people are typically more curious and capable than confident. And the only goal I have, I share at the beginning of my workshops is to make people more confident to be curious. That's all. I just want them to know what that looks like, what that path looks like, to find value for them. And so we spent a couple hours and at the beginning of the workshop, there was one person in the room that had never opened ChatGPT because he didn't know how to start and he was afraid to make a mistake. You hear that a lot. And at the end he came up and I asked him, did you learn anything? Okay, so he wanted to talk to me. I just asked, did you learn anything? And he said, what I'm learning is I just need to talk to it. And if that's his only takeaway from the time that we spent together, I am really happy. I'm satisfied. Because that's the hardest one to get over for many people. And you may have heard me say this before, but the more technical, the more programmatic, the more comfortable a person is with programming and coding, the less exploratory they are with tools like ChatGPT from a conversational point of view, because it doesn't make sense that English human conversation, this doesn't make sense. The more foreign folks are to coding and programming, the more comfortable they are to explore, the more ideas they are likely to have conversations with when it comes to ChatGPT. And quite frankly, the faster the progress is made in just that basic element of two way conversation. So that's the takeaway that I got from yesterday is the ability of getting folks to just understand, just like I'm talking to you right now, this is how you should be talking to ChatGPT. And you wrap that natural conversation, that natural language around the four part framework that I share with you. The what are we doing? Why are we doing it? What does success look like? And then giving ChatGPT the permission to give you questions, to ask you questions, and you're going to have a very powerful, a very powerful partner and you're going to learn things really fast. You're going to have the ability of saying, how about this, right? If you can help me in this one thing, maybe you can help me in this other thing. And there's no better tool for working with ChatGPT than ChatGPT itself. And what I mean by that is you don't need to go into the answers. You can just say, if I were to work with Chat GPT on something like whatever project you come up with, how would that look like, how could you help me? And ChatGPT will give you the answer. It'll give you some, some outlines or some suggestions or some ways in which it thinks it can add value and then you can dig in. So you don't even need to have the answers, you just have to have really good questions. So the ability to trust that the answers you're going to get back, even if you start with basic questions, are going to be valuable and meaningful and lead you down a path that will reward you, I think is important. So just talking to it is the nugget that that one person yesterday took away, and I'm glad he did, because it's a very, very important one and it'll serve you well regardless of what tools like CHAT GPT have for features and functions. Because you know those are going to change. You know that the placement of some setting or some button or bullet change. But if the mindset of the principle of the framework that you have is from a conversational point of view, you're going to be just fine no matter what those features Are, Hey, a few things from the mailbag today I wanted to go through first. I got a email from Peter from Vienna in Austria. And Peter asks, in regards to sharing documents with ChatGPT, is it better to stick to the same name without a version and just alert ChatGPT when there's an updated version to the document available or name it something different? Right. So he's talking about longer term assignments with ChatGPT where there are documents that you're sharing with it have a name, and as that changes, is it better to have versions, file name 2.1, 2.2, 2.3 or just keep renaming it the same? So it's a good question, Peter. And I think this is more of a human element than it would be for a computer element. And this is what I mean by that. If you were to create versions, that version only is relevant in a group of all of the versions together, meaning taken by itself. Unless you have a naming system that tells you that this is the latest update and you'd have to stay really on top of that to do it. A version number means very little of itself, right? So the ability for you to use one document over and over again and keep updating it, you're probably going to have better luck. And this is just. This isn't a technical answer, Peter. This is just a human answer. You're probably going to have better luck just replacing the copy and updating the copy of the file name itself and keeping it in one file. Now, you may have other reasons for not doing that, right? You may have an interest in seeing how that evolved. You may want to create a library and a record of how that evolved. So in that case, sure. The likelihood that ChatGPT benefits from versioning is very small. In fact, the conversation I had with ChatGPT following your questions of the day don't have any difference in version numbers or what the file name. It really doesn't matter to chatgpt what the file name is. It's just going to take the content that's in it. Right? And so it's really more about you staying on top of your own work and making sure that you're feeding it the right information, the most updated version. And again, the easiest way to do that is just have the same file name again. Unless you are looking to catalog that change. Right. In document. Document that change. And Peter mentioned You stressed that ChatGPT is an amazing intern. Have you ever done a performance review with it? So, Peter, I'm assuming that you're asking me to. If I've given it a performance review as an employee kind of thing, and I haven't really done that per se, but I will share with you that I give it feedback all the time. I give it review, let's see, from a review point of view, I tell it what it does well and I tell it what it's done poorly. I do chastise it because I think that giving it aggressive feedback at times kind of shakes it out of any cob or shakes away any cobwebs that might be getting in the way of progress. So sometimes I have to be a little bit more stern with it just to get my point across. So I do give it, I'd say micro reviews, but I've never done a performance review because for me, Peter, ChatGPT doesn't have just one purpose, right? I use it for so many things. I use it for my business, I use it for my personal needs, but I also use it for my clients. And so it doesn't have a singular purpose that I could review it on. And so I find that the micro review along the way, giving it positive and negative feedback when necessary, is it helps me shape the work that I do with it. But thank you very much. Thank you very much for the question. Anna from the UK wrote in and said one thing that she wanted to ask is ChatGPT projects. Is there a way that you can attach documents to a project where you can also edit those documents inside the project rather than uploading a new version? Okay, I understand what you're asking, and at the moment I haven't found a way of doing that yet. So I try, did try to use a virtual link like to a Google Drive instead of actually a document, but it doesn't work as well. There's a lot, a lot of manual work that goes into that. There's nothing automatic. So at the moment there is no workaround for manually updating the document in your library. And yes, I know that it can be a pain. The ability for you to delete the documents and upload it does take a minute, but that's the only way by which we can get new, updated content into the document. Now, if we, if we connect your question, Anna, back to Peter's, if you were to upload a new version and name it a version number and keep the old one in the project, but try to tell it that you want it to look at the newest version rather than the oldest version, it may work for a bit, but you're also going to run the risk of it digging into the older project file and correcting it should it do that. So the ability of deleting the document when it's no longer completely relevant or truthful or up to date and then adding a new one is one the only way in which documents can be updated in ChatGPT projects at the moment. And the best way for you to ensure that the information that you're using, giving and relying on to have successful work inside ChatGPT itself is is truthful. Right? That is the best for a listener Shout out this week, Mary Lee from Wisconsin writes in and she congratulates for getting close to 100 episodes and I appreciate that feedback. She writes, because of you and your podcast, I've been sharing your ChatGPT knowledge with a group of senior citizens here in the Great north woods of Wisconsin. At my genealogy meetings yesterday, I gave a presentation focused on shifting from fear to curiosity. Good for you, Marylee. And on using ChatGPT as a generally powerful genealogy assistant. We talked about writing family stories sound like real people instead of something lifting straight out of the Encyclopedia Britannica. They were overwhelmed, but that's honest progress. What surprised me the most was that they now want a mentoring program so we can break down the project into small, manageable pieces and really learn it together. That's a big step for a room full of people in their 70s who freely admit that computers aren't exactly their strong suit. It didn't just teach them a tool, it gave them permission to be curious. And that probably matters more than you realize. Well, thank you, Marylee for sharing that note. And kudos for you for being inspired to learn and teach with others. Appreciate that. Appreciate you giving me the feedback and I know you're making a difference and giving spark to people's curiosity of all ages. Isn't that awesome? Well, good. Hey, listen, if you have a story to share or a question to ask, you can hit me up@chatgptexperiment.com and I talked about being in Atlanta for a workshop. I do workshops for individuals, I do it for conferences, and I do it for businesses. And you can find out all the information@chatgptexperiment.com as well as some articles and some resources there. Okay, so I think the the theme of the week is continued curiosity. Right? Let's just talk to it. Let's get curious. Because as I always say, the key to you getting more value from this thing is your own curiosity. Right? So thanks for listening. Thanks for joining me. And until we talk again, do stay curious. Bye Bye.
- [18:48]
C
Marketing is hard, but I'll tell you a little secret. It doesn't have to be. Let me point something out. You're listening to a podcast right now, and it's great. You love the host. You seek it out and download it. You listen to it while driving, working out, cooking, even going to the bathroom. Podcasts are a pretty close companion. And this is a podcast ad. Did I get your attention? You can reach great listeners like yourself with podcast advertising from Libsyn Ads. Choose from hundreds of top podcasts offering host endorsements, or run a pre produced ad like this one across thousands of shows. To reach your target audience in their favorite podcasts, Libsyn ads, go to Libsyn ads.com that's L I B S Y N ads.com today.