105 | How to maximize ChatGPT: 7 powerful use cases you need to know with Artur Sossin

29:07Because sometimes it has a different, let's say, perception of what is it, what a sketch image is and how is it supposed to look like, essentially. Okay, so let me get out of here. Yeah. Okay. We also got a download link for that. I'm just going to restore that. There we go. And I think the cool thing here that you're doing is not just creating images, which kind of everybody knows how to do, but we're manipulating existing images. And those original images can be either AI generated or other. So you're literally asking for it to create a new version of an existing image to whatever the needs you have.

29:50And sometimes you need it in a different format. Sometimes you need it with a different resolution. Sometimes you need it in a portrait instead of landscape setup because you're doing a story versus a PowerPoint. Like whatever the case may be, you can transform existing images into other outputs using this kind of this methodology. Yeah, absolutely. And maybe I'm just going to show one example since it's fast and just show you how you can also compare it side by side. I'm just going to input another image I have here of a model that I was using for branding purposes. And let's try the other prompts.

30:32Try out here. Okay, we're going to sharpen the image and we're going to say compare it. It's saying display side by side. Still getting the download. Okay.

30:47So it's basically doing the same thing. It's just going to input two images side by side, but the rest is the same. And as you can see here, I'm sharpening. I'm not doing a sketch drawing. You could do sepia, you could do grayscale, you could do, I don't know, some kind of toning. Anything like that is pretty possible. And yeah, there we go. So we can't see it from this scale. It does look sharper. Yeah, it does look sharper. Indeed, it does look sharper. All right. But you could try all sorts of other transformations. They're in the notes. So basically use the same simple prompt and you can exchange the transformations, chain them.

31:26And we can switch to, I would say, my favorite cases, which involve data analysis and machine learning. So data analysis is number five. I'm just going to get out of here. And here, I actually use 4.0, but only because I want to use the new beta feature, which is the interactive charts that are native in ChatGPT. Again, if you're doing advanced data analysis with a lot of instructions, like the machine learning case, use 4.0, forget the interactives. Probably they're going to make it available for all models at some point. And I'm just going to copy the prompt here. Let's see. Okay, you're an expert data scientist.

32:07The task is to perform a detailed analysis of this data set. You'll then propose different types of charts based on your analysis. And then you propose only charts that support your new interactive feature. As I said, this is optional. At some point, this will be not needed. Then you create the charts, display them. We'll do this step by step. You'll let me review the results at every stage. Notice what I'm doing here. I'm breaking it down because for each chart, it's going to scroll through the data, analyze it, generate the code, execute the code, visualize. And one note I'll make here is that you can leave out the specifics, but then it tends to break.

32:45So it generates the wrong code, executes, oh, I did this wrong, and then I'm going to redo it. The problem with the environment is that when it does that too many times, it's out of context. And for some reason, it breaks. So it just says error in generating or something like that. For text, you usually get continue generating, something like that. But if in one message, you get a lot of code generations, one after the other, and it just broke. And then it's trying a new one and it can't finish, then it steps out. And then you have to do it all over again. So a few points. I will let you run the prompt as you're doing this.

33:18And I'll give a few, again, some additional hints and tips. for best results, don't upload XLS files or whatever the Google Sheets extension is, but actually CSV, it just works a lot better. So that's exactly what I'm doing. I know I'm telling the people who are listening or watching us. So CSV files work much better. They're much smaller in size, and they're also easier for a computer to read. The other thing, as far as the data you want to upload. As humans, we like to tear out Excel charts and tables and make them fancy, meaning we add one column space between each month and two columns space between every year, and then we column them black, and then we add another table on the side that does something else because we want to reference one to the other when we're looking at this.

34:07It confuses the hell out of the machine. And so if you want to use the data for chat GPT analysis, and those of you are not watching, it's generating amazing charts that you can interact with and change the colors and change the type of charts and do really cool things with it very quickly in ChatGPT. But to do that, you need the data to be as clean and simple and sterile as possible. And then you'll get amazing results very quickly together with the analysis that Artu will share with us in a minute. Two tips. One, CSV. Two, clean the data before you upload it because then what happens if you don't, it does exactly what Arthur said.

34:49It's going to try to clean the data on its own. It's going to waste a lot of time. And in many cases, it's just going to fail. So save yourself that step. For people who use regular data that they have in their company regularly, whether it's financial information, marketing information, whatever, OEP data, like whatever data you have exported as CSV or in Excel, just create another tab that has the same exact information that's in your fancier table, but just the data and upload that as CSV to the model. while still you can run on your fancy version of the data.

35:22Truly agree. And we can go through the analysis. Went through it in one shot and we can interrogate it later. So the new interactive feature, as you can see, we have an interactive table so we can actually ask questions with respect to columns or rows or segments of the data that's now possible. What else? Okay, so it recognized what's in there. I used a classic churn data set for us. And then it said, okay, the number one inside is whether customers churn or not, how many. Okay, so it did a pie chart of that for us. Then churn rate by contract types. So we have one year, two years, month to month.

36:03And again, we have no yes. And yeah, you've seen this feature by now. It's still pretty limited. You can actually tell ChatGPT to use a library called Plotly to create HTML graphs for you. And there you can embed stuff in your data points and whatnot, like much more than this. I'm not going to show it today, but I'm just saying that's probably where they're headed. Today, it's just colors. And that's not, that may be helpful if you're more sensitive to some colors than others. But I can't even take out the legend, so to say, toggle contract types, for example, and focus on one. Or change the font or the size.

36:36you're very limited with what you can do. Exactly. But it's beta. I think what is helpful is when you have a lot of data is that you can really go through here and see what the numbers are. That's helpful. Here it's small, but you have more like this one here. I think this is very good, like line charts like this. So I explicitly asked for the three types of charts that work today with the beta, more or less. And here we have churn rate over tenure and compared churn and no churn, right? And we can ask it questions about this, right? We can ask it for more charts. We can, what else? We can ask it to regenerate these, adjust them in some form.

37:13But what I'm going to do is I'm going to go here and just ask it a question about the data. For example, I'm going to say monthly charges. So how do monthly charges relate to churn or melt churn, for example, right? And in this product, I haven't used any advanced techniques, nothing, like literally nothing. So it's really like going in from a high level. I have a structure. It's structured. Yes, it's a table CSV data set. So that helps. What is our set is very important, I think. So with unstructured data, it's going to have an issue. Essentially, it's going to try to structure it and most likely fail.

37:55So if you have tabular data, perfect. Then it can really work wonders with that. and you can really talk to it like you would talk to a data analyst essentially, right? Okay, so generally the box block for us, distribution of monthly charges for customers who have churned versus those who have not. Here are a few observations. Customers who have churned tend to have higher median monthly charge compared to those who have not, okay? There's a wider spread of monthly charges among customers who have churned. So as you can see, we can go on, right? We can interrogate all the other characteristics that we have in our data sets.

38:27We can do other plots and basically have a intern data analyst at our side, right? Yeah, I'll say two things about this because I'm with you. I think this is one of the most incredible capabilities that they've added. And I used to run a pretty large travel company, like a hundred million dollar travel company. And I had a data scientist team and we had huge databases and did a lot of cool stuff. But every time I needed something, I needed to write a really long detailed email to explain exactly what I want from the data team. And then they will spend either a few hours or sometimes a couple of days to figure out how to write the code to make this happen and then create the dashboards for me so I can see what I wanted.

39:08And literally now with this capability, I can get the answer faster than it would have taken me to write the email. Forget about, wait for them to actually write the code and do the thing. And the other thing that happens is the iterations. Is that the other thing that Ardur mentions? You can keep on going. because every time what would happen when I go to the data team, they will give me what I asked for, which sometimes would be exactly what I envisioned. Sometimes it wouldn't. So whether I had to change it or sometimes it was exactly what I wanted, but then I had a follow-up question that I didn't think about because I didn't see the data.

39:39And now you have to write another email. You have to wait another day. And here it all happens in seconds or minutes. And you can just iterate and keep on diving deeper. And you can do this for sizes of data that you cannot even do in Excel. Like I played with this with data files of 250 ,000 rows, which you just cannot upload to Excel, just won't run. And you can do it here and you can get results. It takes a little longer, but okay, you're going to wait a minute and you've got to get an answer. It's absolutely magical. Absolutely. Absolutely. Yeah. Many use cases. So customer turn, yes, but you can think leads.

40:17You can think, I don't know, your marketing campaign data, whatever. Financial information, hiring, like literally any data that you have that is numerical data, you can run through this through as many years back as you want. It'll be able to run. Pretty much. Yeah. Until it runs out of RAM, I think. Of context. Yeah. By the way, the other interesting thing, going back to this, before we switch gears to the next one, you can upload two separate sets of data. and if it has some connecting information, it will know how to connect them together. So a simple example, if you look at churn, okay, we upload this churn data, but let's say you also have data from your financial platform saying who paid late.

41:02And if you have the same customer names, then it will know how to connect the two together and we'll give you, now you can do more analysis. And let's say you also want to upload external information about how the economy is doing. So now it's going to connect date as far as the connecting information. And it knows how to do all of this on its own. And now you can do more and more detailed analysis, combining different data sources without having to know how to do the actual technical work behind the scenes to know how to do that. Absolutely. Absolutely. Having the domain knowledge helps because you can guide it better.

41:37But even if you don't have it, this is how you get. I explicitly showed this first. The number seven will have more domain knowledge, let's say, related to data science. But this one specifically starts at a very high level to get you going. Awesome. And now we're going to switch to presentations. So I'm just going to start a new chat. And four, again, since it's more complex. And we're going to look at GDP per capita in the EU, right? So I'm going to let this run, and then we're going to read through the prompt. I think I'm going to make this shorter so that it doesn't overload the message gap.

42:16Maybe I'm just being mindful of the last use case that we have. Just a thought that came into my head. So we have five slides here. So I'm going to put it to maybe four, essentially. Yeah. Maybe even three. Okay. Nah, let's keep it four. So we have introduction page, trend description. Oh, let's keep it five. Too many things to change. Let's keep it five. If anything, we switch to 4.0, it's always a good fallback. So no input here, no input here. It's going to do everything natively. So what are we doing? We have a thing that is skilled in presentation creation. I'm not giving it a very specific role.

42:57I don't know, a comms expert or something. As I said, it doesn't really matter. The task matters and the instructions matter most. I think at this point in the model's evolution anyways. Okay, striking PowerPoint presentations, that's what we want. We want a short presentation about GDP per capita in the EU aimed at a non-technical audience and a step-by-step guideline. Retreat the data by searching the web. Write clear and concise content for X number of slides. Then there's a description of the layout and the formatting. Then we have five supporting images that we want. Let me review the images in the text before proceeding so that, again, splits the flow into segments so that we can inject our corrections if we want to.

43:40and so that we limit the model's attention to a subset of this task and not generating everything with one shot. If you do this in 4.0, it will do that. Despite me entering, let me review this everywhere, it still just goes, okay? Execute code to convert to PNG because we have WebP as a native format and that is not supported for exporting as PPTs. That's the last step we're going to do is just kind of combine all of that. It's got a write code behind the scenes to combine the text and the images into an exportable PPT file for us. And it's already started. So as you saw, I searched three sites.

44:22Okay, got some data on the GDP per capita. Already created a layout for us. And yeah, started generating images. It selected the images for us at this time. It didn't let me review them. How nice. Okay. So yeah, so as you can see, like some of these images could use some work for sure. And especially like with the text and everything. So I would basically edit this out. So either here natively or I would just let it regenerate. But for the sake of time and messages, I'm not going to do that. I'm just saying that this is possible if you're not satisfied with the images. I chose minimalistic style explicitly so that not, we don't have excessive complexity in them still.

45:04it inserted some data some names since we're talking about countries and gdp right yeah but you do see recognizable landmarks here okay so what then again repeating the layout and asking me to review it or i'm going to say okay just proceed as i said we could edit it we're not going to do it today and two things about editing so because it's we're doing multiple steps you can edit specific steps just by there's a little pencil thing next to your prompts and you can go back if you guys don't know that then you can edit specific things but in this particular thing the really cool new feature new they had it for a month it basically gave it basically gave arthur five slides like what's going to be the header and what's going to be the topics and the text in each slide and let's say you like all of them other than one you can literally highlight a section of the thing that ChatGPT wrote, of the answer.

46:02So highlight a section and then little two quotation marks show up. And then you can ask it to change just that. So it gave you five slides. You just want to change slide number three. You can highlight slide number three and then everything else comes up in exactly the same word to word the way it was before. It's not really regenerating it. It's only regenerating the section that you highlighted and changing that based on what you're going to tell it to change. So that's a very important use trick that they have that's now available both here and in Gemini for the last like month and a half or so.

46:34Yeah. Oh, you see, it made an error. That's what I was talking about. So that happens. That happens. So it's a generated folding code and it's retrying that. But anyways, I would say here, if you really want to get the best out of it, I would break this down further and add details to layout specifically and to the images that you want. So really do it iteratively. So maybe like kickstart it with a general task, let's say, or maybe step one, but then research, get the content in, and then start one prompt after the other. Okay, let's work on the text and the layout, polish that, then go to Dolly, make detailed prompts for each slide.

47:22then say, okay, I'm happy with this, now package it. So just use elements from this prompt to package the final results because then you will have better raw components to work with, so to say. And that's the whole point with this. It's not gonna give you a polished presentation. Even if I'm very explicit with the details of the layout, et cetera, it's still not gonna give me a polished presentation. I think the value here is two things. So one, you get raw components in a PPT format. You can work with it there. And we have it now. See what we got. I'm just going to download it here and open it.

47:59So that's one benefit. The other thing is, I think I have one comment saying on this post, yeah, what's the point? Presentations are not about this. They're more about communicating with the audience. And I agree. But in some cases, in companies particular, that's where I learned the fact that you can do code and generate PPTs is that we use it for documentation. So that's a documentation medium in the company for certain things. And then it's not about being polished or like one message, one slide kind of thing. No, it's about just documenting in a PPT format because that's the recognized thing in the organization.

48:31And then you don't want to spend time on your results, right? Doing all this manual labor of dragging things in PPT, resizing, whatever. You just want a standardized way of your results being deployed to a PPT. And that's where something like this can also come in handy. Yeah. And by the way, connecting this back to your very first example, you can upload your existing presentations and say, these are the formats we're looking for. So it's not going to follow the color guides and stuff like that, but it is going to follow the layout. So if it's a always side by side, 50 % image, 50 % text, size of the header, all of that, it will know how to learn and create that.

49:09So when you open it in PowerPoint in your company, all you will have to do is apply your company template. And it's not going to make everything look really weird because it's going to more or less follow that same formatting to begin with. So you can do that as well as far as saving yourself steps and manual work afterwards. We have also dedicated tools for this, like Gamma, like Tome, for example. So you have options, I would say. Yeah. Yeah. Okay. So important. Yeah. Yeah, this is not the best result I've gotten, but I'm going to show it anywhere. So it's as unscripted as it gets. Yeah, there we go.

49:46I think that's visible. For some reason, we got an empty slide. Never mind that. Okay, EU GDP for cabinet. And this is what I'm talking about. So just dump the image over the text, right? The text is over here. I have gotten better results where the text would actually be on top of the image or to the side of the image. And that's what I'm saying. I'm not being specific enough with respect to my layout in this prompt. That's what I recommend as a direct upgrade. But in general, it took all the images that it had, her slide, took the text, right? Made some conclusions, observed the trends over here.

50:21And we have our raw materials to work with. And then you can just apply templates here and continue from here. Yeah. Awesome. Going to shut this down. And then last but not least, I hope this runs. I hope this runs without breaking. is most more likely machine learning right so this is like building on the case number five where we just did simple data analysis and now i'm going to do something more advanced so i'm going to use a bank loan data set which is related to leads actually we want to identify the customers for uh remarketing this case based on the features and what i'm doing here is what set, I have two data sets, which have the same type of columns with one exception in the test data set where we don't have a loan approved column.

51:12That's what we're trying to figure out. So in the train data set, we have an approved loan column, which we're going to use to train the machine learning model that we're going to apply to the test data, which is basically new data that's coming. Think of it this way. And I have a template here, but the example is already pre-filled. So the template's, let's say, more free to use. So you can really do a lot of things with this. But the important part is two things. So one is, again, a step-by-step instruction, right? And it's much more detailed now. I'm just going to launch it so that we can read in the meantime while it's running.

51:51So expert data scientists, your goal is to use the data set described in context. The context will contain the data sets and their descriptions. You will We use the data sets to train a machine learning model in five steps. You will avoid displaying intermediate information while performing each processing step. Display the summary of each step. Stop before proceeding to the next step and let me review your progress. You will ensure that all variables are passed from one step to the other and nothing is forgotten. Here are the steps to train the machine learning model. And then I break it down into steps.

52:21You can do even more granular breaking. Each of these steps contain a couple of sub-steps. So cleaning data sets. Then we check for outliers, not a number, missing data, whatever. Feature engineering. So this can be custom to your data set. In this case, I'm really using some of the knowledge I have about the data, what is there. And I think that's important for successful results. I highly recommend that most of the time you do know your data, you do know your variables. So include that. Much better performance this way. After that, we perform pre-processing. We split into input-output. We split into test and train.

52:56I make some references to libraries since it doesn't have all the libraries in its environment. I make some, let's say, nudges here because sometimes it just leaves out all the things that it did in the previous step for some reason. So I've got to remind it, okay, avoid the not a number, et cetera. Even so, it might break. Let's see. Then you train the model. So everything's prepped, right? So we clean the data. We've done some feature engineering. We've done the preprocessing. Everything's ready. We just have to fit the model. and that's what it's done here. And then some parameters, confusion matrix, ROC curve, receiver operating curve is one way of measuring performance for machine learning models.

53:37So we're going to look at that to see if our model is doing something weird or it's looking good. Then once I'm satisfied, then we can apply it to the testing set, make sure that pre-processing matches the one performed for the training set, and then display certain visualizations. You can pick and choose whatever you want. And then suggest the thresholds for hot leads based on conversion probabilities. All that to get that threshold. All that to get to a point where I have a model that makes a prediction for me on which customers are hot leads for me. And gives a recommendation based on that and reasoning for that, actually.

54:15The context basically contains all the columns that I have in this data set and the CSV and their descriptions. And this will help. You can ignore that and then let ChatGPT figure this out, but this will just guide it better and reduce the probability of it breaking down in the middle, right? Two data sets, train, test. And you notice that I'm using curly brackets or over. This is just to focus the model on certain aspects of the prompt because this is a big prompt by now, right? So we want it to really focus on certain key elements of that prompt. So that's why I'm using these curly brackets.

54:50And yeah, it's done data cleaning. did a summary for me and asking me to proceed. I'm just going to say proceed because I've seen this way too many times. As we're waiting for it to do its thing, I will, again, summarize this very quickly. What this allows us to do is to take a pre-existing data that we have and use it to train the model without really knowing anything about how to train models. And again, as Arthur said before, if you know what training models is, it helps because you know what to ask for and you know what you beware for. But even if you take the prompt as is from Artur's document that he's going to share with us, you'll be able to do most of this just by adjusting it to your columns and so on.

55:32But let's take it back to the existing example. You can take the data of all the customers you have who churned together with all the information you have about them, when they pay, what they paid, what they've used, what licenses they have, how many people. like all the data that you have, put it in a table, ask ChatGPT to train on that data, and then load the data of all your existing clients. And it can tell you which ones are likely to churn and why based on the historical data. This is obviously a goldmine for predicting anything, whether it's financial information, marketing information, spend, inventory, churn, like literally any information you can imagine that you have historical data for and that you want to project based on your existing data.

56:17Yeah, absolutely. And I know one more thing is that I used to spend hours on this, like literally, because I've done machine learning, I've done deep learning, I've done generative AI. Machine learning, although it's less complex, it's supervised, you still have to put a lot of effort into feature engineering, into pre-processing, and this is just faster. So again, this might not deliver the, say, end result that I'm satisfied with, but it gives me a head start. I know I already have clean data. it tells me what it's doing, what is wrong with the data, et cetera. So usually you have to investigate that and you have to write code for that.

56:53That's how the process worked. And that would be hours. Now it's minutes, literally minutes. And what it's done so far is that it went through the cleaning. It did feature engineering that was successful. It did pre-processing as we instructed. So it split it into a training subset, validation subset, but did class rebalancing or rather it's trying to do class rebalancing and I hope it will break. And this is what I'm saying. So this is already gets to that level of complexity where it is retrying despite the specific instructions because it used the library that I actually explicitly said not to use.

57:28So I said use something else, but it's still using in Blur for some reason. But now it's done it. So it stepped aside once, twice, but we have preprocessing now. And now we can actually proceed to training the model. And I'm using a logistic regression here. Any machine learning model can be trained in this environment. Some neural networks, basically lightweight. Some small unsupervised approaches like clustering also work. But deep learning, you won't make that because the RAM is limited and you don't have GPUs. Even if you don't have GPUs, you can do CPU, but the RAM is just limited. Those models are huge.

58:07The image data is also big, so that will not run. but that's just an environment limitation. It's not a JR to VI limitation per se. No, I think this is amazing, right? I've done very little of this to that level. And I think it's absolutely amazing. That's like next level stuff where you have the data and you can now do stuff that before you needed an actual data scientist on your staff or hire a third-party company to do this for you. And as you're saying, this may not be good enough for everything you need to do, but it's good enough for some of it. And it may give you great ideas on how and where to start to find useful information.

58:48Yeah, and you can always tell it to explain it to me. I don't know anything about data science. But I'm sure you can break it down further, abstract it away. And I think that's where the value lies. One thing, though, again, like back to hallucination, is that it can hallucinate code sometimes. It helps to at least check that it actually is working with the data that you have and not inventing something. Now, with huge data sets, I haven't seen this, but when I was working with lists sometimes, like when I was doing lists from web search, it literally generated fake entries into the list rather than adding the links.

59:26So when I look at it... It happened to me as well. So I can verify that it's doing it. I was trying to use it to quote unquote scrape data that I needed for a test case. So not using actual client data for something I teach in my courses. And I was trying to collect data from a website into a table. And it created a perfect table. And it seemed perfectly fine. And literally 100 % of the data was made up, even though it all existed on the website I gave it. So yes, it definitely does it sometimes. Okay, now it says it's taking too long and our dimensionality is too big. So apparently I just deviated.

1:00:03I think we're good. Listen, I think people get the point, right? You can do basic machine learning and then data analysis using data sets that you have. And whether this one works this time or not is not a big deal. I'm going to show you how this looks like. Yeah, how the outcome looks like. Yeah, that would be awesome. Yes, exactly. So sketch, churn analysis. What do we have here? Yeah, machine learning. There we go. Okay, so that's where we're at, I think, is here, right? So training data set. But yeah, so if it succeeds in there, it would give you the confusion matrices. It would give you its interpretation of the parameters.

1:00:42It would give you the visualization of those parameters, essentially, the RSC curves that we asked for. Again, interpreting those as well, then it'll proceed to the testing set and predict the probability of conversion, in this case, approved load. And then it says to me, okay, yeah, threshold of 0.5 is good because then we don't get too many false positives. And then I say, okay, optimize, adjust the threshold. And it says, okay, these are the options that we can have. And then I say, use cost benefit analysis to optimize it. And then it does that. It makes some assumptions on the cost for a false positive, a false negative, and the gain we can get from a true positive and does some optimization.

1:01:26And And with that, I also asked it to visualize that. And the visual is actually, for some reason, not rendering. But the point is that it really went deep and you can actually give it something rather than use assumption and say, okay, the true negative or the false positive would cost this much, but the true positive is that much gain for us. So these are your boundary conditions. And then it would do that. So that's how it can look like. As I said, this prompt is pretty complex. And sometimes it just like somewhere in the middle, it just takes a detour. let's say. This is awesome. Arthur, this was amazing.

1:02:01I really didn't think we'll be able to do all of this in an hour, but you prevailed. We covered a lot of stuff in really a short amount of time, but in a lot of depth and a lot of detail. Arthur is kind enough to share that in a file with all the stuff that he just shared. So that will be in the show notes once the show goes live and on the Leveraging AI podcast, as well as on the Multiply AI YouTube channel. So on both of those, we'll be able to have a link to the document. Arthur, this was absolutely amazing. Like literally pure gold across multiple aspects of the business. A lot to learn from, very practical, useful stuff for literally every aspect of the business.

1:02:41If people want to follow you, learn from you, work with you, what are the best ways to connect with you? LinkedIn is the best. Just reach out. I'm there almost every day. Awesome. Thank you so much. Thank you. Thank you for having me.