Prompt Engineering for ChatGPT: Master Generative AI Prompts

1. Course Introduction: Hi, guys. Welcome to my course on prompt Engineering for ChatGPT. My name is TamoyKumar Das. Just to give you a background about myself, I am an ex Google employee with 16 years of experience into paid advertising, and I've been teaching paid advertising for more than ten years now, and I teach to a lot of young professionals and entrepreneurs and experts who want to get into this field. I wanted to take this opportunity today to let you know what we are going to learn in this course. So we're going to look at understanding the capabilities of genetive AI. Applications and various tools of genitive AI, including hat GPT, how we can use them for various use cases. Then we will get into understanding prompts, which we can give on Chat GPT specifically prompt, which is going to be different types of patterns of prompt which we can have. I'll show you various examples of these prompt patterns, which you can apply in hat GPT and get really great results. I hope by the end of this court, you understand how you can use prompt engineering effectively on Chat GPT as a tool. Thank you once again, guys, for enrolling into this course, and I'm really excited to see you inside the course. 2. Why Generative AI Matters: Hi, guys. Welcome to this session. In this session, we'll understand why we should be learning about genitive A. If you look at it, genitive AA is on the minds of every leader in the organization right now. Businesses, governments, and with interest comes opportunities. Organizations are specifically looking for people who understand the technology and most importantly, have the skills to apply it practically in day to day work. Now, unlike many of the previous trending technologies, genitive AI touches almost every role in every profession at this moment. Now because of which, genetive AI skills are expected to become more important in the coming future, not just for computer scientists, for everybody, which is why they will be essential as word processing, spreadsheets, even basic business literacy. Now there is a lot of new interest happening right now in AI and businesses are looking beyond customer AI, consumer AI. A chat booard interface is a great way to demonstrate generative AI potential. Now, real life use cases are embedding generative AI into existing processes and making it an integral function of nearly every single business workflow. The skills you will be gaining as part of these programs that should help you with your career and be very applicable to your job instantly. There are a lot of plus points with learning about genitive AI because this is going to be useful not only in your day to day professional work, but personally as well, you can use these AI tools to solve a lot of problems, questions, queries which you may have. The tools helps to get to the real solutions and gives practical steps as well. So you can instruct the tool in such a manner. You can prompt it in such a manner that gives you the outputs which you're actually looking. So it makes a lot of sense that we learn about generative AI, understand how to use these AI tools in different spheres of work. In this particular course, we're going to look at how it is going to help in our sales roles in sales profession. 3. Introduction to Generative AI: Hi, guys. Welcome to the sessions. And this session, we'll talk about the genetive AI, understanding the overview of it, the background of it. If you look at it, artificial intelligence or AI has been around for years, shaping almost every sphere of our lives and revolutionizing how we live and work. At its core, AI can be defined as the simulation of human intelligence by machines. AI models learn from vast amounts of existing data. There are two fundamental approaches to which is discriminative AI and generative AI. Now, discriminative AI is an approach that learns to distinguish between different classes of data. A discriminative AI model is given a set of training data where each data point is labeled with its class. The model then predicts the class of a new data point by finding the side of the decision boundary that the data point falls on. Discriminative AI models use advanced algorithms to differentiate, classify, identify patterns, and draw conclusions based on training data. They cannot, however, understand context or generate new content based on a contextual understanding of the training data. This is where generative AI, intelligence or generative AI comes into picture. GentivI models learn to generate new content based on the training data. They can capture the underlying distribution of the training data and generate novel data instances. GentI starts with a prompt. This can be text or an image or a video or any other input that the model can process. As an output, the model generates new content, including text, images, video, audio, port, and data. Gent can produce output in the same form in which the prompt is provided. For example, text to text or in a different form from the prompt such as text to image or text to video. Now, generative models can take what they have learned and create entirely new content based on that information. Both discriminative and generative models are created using deep learning techniques. Deep learning involves training artificial neural networks to learn from vast amounts of data. An an artificial neural network is a collection of smaller computing units called neurons, now, which are modeled in a manner that is similar to how a human brain processes information. The creative skills of genetive AI come from generative AI models such as generative adversarial networks organs, variational auto encoders or VAE or transformers and diffusion models. These models can be considered as the building blocks of generative AI. Now if you look at the evolution of generative AI, it started off in 1990s when the origin of machine learning started off and then they got into exploring arithmetic data creation. From there in 1990s, neural networks came into existence with advanced genetive AI capabilities. In 2010, deep learning started off with large datasets, computing accelerated generative AI. Then in 2014 and beyond, Gans which we talked about, and other models regularized the whole genetive AI. Now if you look at the foundational models, the EI models with broad capabilities adapted to build specialized and advanced models or tools. Large language models came into existence, which could process and generate text. In 2018 onwards, various types of LLMs came into existence like Open AI, GPT N series, starting off with GPT one, GPT two, three, 3.5 and four. Then also Google Palm came into existence, Lama came into existence in 18 itself, there are also AI generative image generation started off with stable diffusion and Dali. If you look at the generative AI tools currently which can be used for various reasons, can we One is under text generation, there is tragic PT Gemini. Under image generation, there is Dali two, mid journey, which we can use. Under Video generation, there is synthesia then under code generation, there is Po Pilot and Alpha code. Hope this makes sense. I hope you're able to understand the evolution of generative AI, which has happened over the period of time. 4. Evolution of Generative AI: Hi, guys. Welcome to this sessions. In this session, we'll discuss the evolution of genetive VI over the years. If you look at it, genetiveEI started evolving parallel with the advancement of traditional EI. It remained dormant for over 20 years, but then it got propelled by GANs and VAEs specifically, and now it has poised to shape up the current future. So there was significant progress was made in creating content. So in the advancements of it, the early Geni models had some issues with coherence and quality. Okay? So GPT three, GPT four, Dali, they delivered sophisticated text and images outputs and enhance the creativity and automation. Now if you look at the genitive capabilities, it acts as a creative genius. It can create images, write stories, invent new ideas for us. It is going to be based on a rule based mechanism. It's restricted systems to predefined context and rules. Now, machine learning and statistic models are used wherein it identifies patterns in datasets based on semi supervised, supervised or reinforcement learning. Now there are certain other things as well. The VAs over the period of time started learning patterns to generate similar outputs. Gans produce highly realistic images and art. Autoregressive models were used to generate content step by step, ideal for language modeling. Then deep learning and neural network came into picture which could detect patterns in data with advanced capabilities. It was able to handle unstructured formative data as well. Then the GAS, which is generative adversarial networks, marked the beginning of new era of AI tools where it could create new datasets. Then also there was LSTM and RNNs which were used, which would offer advanced capabilities, handled unstructured data, and could process time series data. Now, if you look at the difference between generative AI and traditional AI, traditional AI analyses or predicts using existing data. Common task can be classification, urigreon recommendation. Whereas genitive AI uses GAS and transformer models, it is able to create new data that resembles the trading data. Now if you look at artificial intelligence or traditional AI, it evolved from basic to predictive order level, whereas generative AI creates human quality outputs using AI techniques. So if you see since 2017, a new era of generative tasks have evolved, leveraging open source GPT models. It has utilized pre trained models for large datasets and fine tune models for specific tasks. So overall, if you see the main difference, traditional AI follows specific instructions, whereas genitive AI invents and creates on its own. 5. Capabilities of Generative AI: Hi, guys. Welcome to this sessions. In this session, we'll talk about the capabilities of genetive AI. If you look at the capabilities which genetive PI has now, it goes on from text generation, image generation, audio generation, video generation, code generation now, data generation as well, and augmented capabilities also it has now got and also helping immersive virtual worlds creation also it is able to do. Now, if you look at specifically text creation capabilities, so there are various LLMs which are providing that, which are trained on large datasets and they can generate human like text. No, they are also able to learn patterns and structures from datasets and generate content and contextually relevant text messages, texts or responses, conversations, explanations, and summaries. Some of the examples of text generating capabilities can be coming from OpenAI, hat GBT, and Google's Gemini. Now if you look at specifically image generation capabilities right now, the generative AI models leverage deep learning techniques like Gans, which is generative adversarial networks and variational auto encoders. With the help of these, they're able to generate AI images which are realistic textures, natural colors, fine grained details. Now, some of the examples of image generation are coming from Style gan, which produces high quality, high resolution novel images. Then there is deep art, which produces complex and detailed artwork sketch, from a sketch specifically. And then there is Dali. Dali produces novel images based on textual descriptions which we give it. Similarly, there is audio generation capabilities right now with generative AI, wherein it is able to generate musical compositions, text to speech, audio, synthetic voices, and natural sounding speech. Some of the examples can be Wave gan, which is producing raw audio waveforms, realistic sounds, speech, music, environmental noises. There is open AIs usenet, which is able to generate original music in various genres and instrumentations, and also can create classical compositions to pop songs as well. There is also Google's tachotron two, which is able to produce advanced DTS, and can produce highly realistic synthetic speech, tone, pitch, modulation, pronunciation, rhythm, and expressions. There are a lot of capabilities of generative, which has happened over the past and it is continuously increasing right now at this moment. 6. Applications of Generative AI: Hi, guys. Welcome to the sessions. In this session, we'll talk about the application of generative AI in different sectors of work. The first one, we are going to look at application of generator AI in IT and DevOps. So here, it really improves the software delivery processes and infrastructure management. The code generation capabilities of genitive AI reduces manual coding efforts and time spent on repetitive tasks. For example, Git Hub, copilot and SNIC Deep code helps to do code repositories. It can examine that, I can examine coding standards. It also helps to generate synthetic test cases and test data. Wherein you can simulate user behavior, impact, software efficiency, reliability, and robustness. There is also tools like APLA tools and testing, which can guarantee adequate testing coverage, increasing the depth and diversity of datasets. Also, apart from this, you can monitor and detect anomalies like IBMs, Watson AIOps and Mok soft AIOps. It can analyze system logs, metrics, and other data like proactive maintenance. It can help in lessening the downtime and also preventing critical failures. Now if you look at the application of generative AI in entertainment, in art and creativity, it can help to generate synthetic content like music, scripts, stories, videos, movies, video games. In game development, there is Houdini by side effects, which can create games, animations, AR and VR experiences, unique characters with unique behavior. Other than that, there's also virtual influencers and avatars, which has come over the period of time, which are able to interact with users and create engaging experiences. Then there is application of generative AI in education like content generation, personalized and adaptive learning experiences, simulated experiential learning, all that can happen now. It can help to provide language translation like making content accessible to different people, grading assignments, providing instant feedback, creating learning journeys and assessment strategies to support learners pace and strengths, generate taxonomies which can be learners performance and preferences. Other than that, generative algorithms are also used in education to detect special needs and learning disabilities, create specific lesson plans, track learners progress over time. You can also do knowledge tracing wherein write pacing and content for individual needs can be done. Tutoring support can be provided. Virtual and simulated environments can be created. Inclusive education can be done. The example, tools which are null J. It's an AI generated E learning, which can be done in minutes for the targeted topic, which can be interactive videos, glossaries, summaries, all that can be done with the tool. Hope this makes sense. I hope you will to understand the various application of generative AI in different sectors of work. 7. Tools for Text Generation: Hi, guys. Welcome to this sessions. In this session, we'll look at various tools which we can use for text generation in LLMs. If you look at it, large language models are based on patterns and structures learned during training. These LLMs interpret context, grammar, and semantics to generate coherent and contextually appropriate text. Drawing statistical relationships between words and phrases allows these LLMs to adapt creative writing styles for any given context. LLMs are the basis of many text generation models. Two such examples are generative pre trained transformer or GPT and Gemini AI model. The models have evolved into multimodal models offering multiple capabilities. Let's learn about the capabilities of these models through two popular tools right now, which is SATGPT and Google Gemini. If you look at ATGPTs based on a GPT as a large language model and uses advanced natural language processing or NLP, which we call it. Well originally HGPT only took text prompts as input to generate new contents, with the newer version, it can take both image and text inputs now. ChaGPT offers diverse capabilities for text generation. It is also capable of smooth and context based conversations. Now, in the same manner, if you look at Google Gemini is powered by Google's Gemini AI model. It introduces a new family of multi model AI models and it enhances reasoning, understanding, and generation. It also ensures efficiency and scalability and optimizes seamless multimodal interaction. It also is able to handle diverse data and task. Let's see some practical example of how this is going to be. This is going to be the Cha GPT interface where we can come and let's give a general prompt wherein I'm saying that I have heard about generative I and want to learn more. She's going to give me a lot of context about what is generative AI. How does it work? LLMs. She's going to give us a lot of related information, which is quite informative and provides the right information about. Now, furthermore, I can dig deeper where I can say that how I can use native AI to specifically improve my storytelling skills. So now I want to divert it into a specific category requirement, which is storytelling skills. So now it's going to give me ideas around that develop deeper characters, improve dialogue writing, use AI to brainstorm better story ideas. Okay, so it's giving me some practical inputs which I can really use to improve my storytelling skills. Same way, I can also ask it a separate thing. Let's say I'm asking you to help me with creating slides to demonstrate the features of a learning platform. Let's say I want to create certain sales slides. So it's going to give me the structure is really good where it breaks down into slides, title, subtitle, include, and then the problem we solve. The focus is given on context is given, which is for learning platform. So it's giving me all the necessary points for that. This is how we can make it useful. Another great usage is you can use it for learning languages. All that is possible, so you can convert any English language to any other language which you want, and Chachi P can easily do that for us. Same way, let's look at Google Gemini, which you can also make use of where you can give a prompt. Let's say, I'm asking you to provide a summary on the latest news on the war in Ukraine. So it's going to give me all the information related to that. You can see over here all the information, the latest information which we can get. Similarly, if I wanted to build a strategy around making a digital marketing campaign for a fashion brand, so it can help me with that also. So now we're asking it to provide a digital marketing strategy. So immersive and AI driven experiences content strategy, authenticity or aesthetic, okay, social commerce and community. So you can see it's giving me some specific strategies around digital marketing, which I can use practically to promote a particular brand. So this is how we are going to make use of both the tools specifically speaking. And then if you look further, so by using CHAPT and Gemini, it has a lot of benefits. Like, it provides problem solving through basic mathematics and statistics, financial analysis, it can do investment research, budgeting, all that it can do. It can also help you with code generation. Now, if you compare CHATPT with Gemini, CHAPT is effective in generating dynamic responses and conversational flow is there in its response. Whereas Gemini is good, optimal for research work, research in current news, information which you want on a particular topic for all that purposes. There are other text generator tools as well, which you can absolutely use, for example, Jasper, which is useful for creating marketing content for a specific brand. You can also use writer as a AI tool, which creates content for blogs, emails, SEO, metadata, and also ads on social media. There is also copy.ai, which creates content on social media for marketing and for product descriptions. There is also write Sonic, which helps provide specific templates for different types of text. There is resumer you classify as well for generating text summarization, text classification. There's also brand 24, which you can use for sentiment analysis, and then there is Weaver and Yandex, which we can use for language translation. That is how text is going to be text generation is going to be, which we can see over here, which you can absolutely use on all these AITunes. 8. Tools for Image Generation: Hi, guys. Welcome to the sessions. In this session, we'll look at different types of tools which we can use for image generation. Imagination models are basically ones where we can generate new images, it can customize real and generated images. For example, let's say we want to generate an image of a child with a book and then change the book cover in a generative image. All that can be done by image generation models. Now there are various types of it. One is image to image translation. You are transforming an image from one domain to another. Example, this can be useful for converting sketches to realistic images, converting satellite images to maps, converting security camera images to higher resolution images, enhancing detail in medical imaging. Now, other tools are going to be style transfer and fusion. These are useful for extracting the style from one image and applying it on another. Example can be converting a painting to a photograph. Then there is in painting. In painting is we're filling in the missing parts of the image. You have an image and there are some parts which are missing, so those can be AI generated. Example, art restoration, forensics, removal of unwanted image objects and images, blend virtual objects into real world scenes. Then there is out painting. Opainting is extend an image beyond its borders. Example can be generating larger images, enhancing the resolution, creating panoramic views. All that can be done. So now from Open AI, there is Dali, which is based on GPT, which can do all of this, can generate high resolution images in multiple styles. It can also create new versions, can be generated can generate multiple image variations can be done. It uses in painting out painting features as well. Then there is stable diffusion. This is an open source model which can create high resolution images. It can generate images based on text prompts. It is used for image to image translation in painting and out painting. Then there is style gan, which enables precise control for manipulating specific features, separates image content and image style. I evolved to generate higher resolution images. There are other tools as well like crayon, free pick and Pick Start, which are also available to generate images in different forms. There is Photo and Depart effects as well, which offers various pre trained styles. It allows custom styles as well. Then there is depart dot IO, which is an online platform that turns photos into artwork. And then there is Mid journey as a platform, which enables image generation which enables image generation communities where artists and designers create images using AI. It also enables exploring each other's creations. Let's look at one of these tools, which is going to be free pick. This is the website where we can come to free pick and we can generate an image here. Let's say we are giving it a simple prompt right now with this prompt, it's going to be text to image generation, which we are trying to do here. So now you can see it has gone ahead and generated that image for us, a boat sailing on a calm lake at sunset, surrounded by lush green trees and misty shoreline in this particular way. I hope this makes sense. I hope people understand now the various tools that are available now for image generation with the help of these AI tools. 9. Tools for Audio and Video Generation: Hi, guys. Welcome to this session. In this session, we'll talk about the tools which we can use for audio and video generation. So in this generative AI, audio capabilities help companies and individuals, novice or experience to simplify processes, bring complicated visions to life. Now speech generation tools are available here, which can be text to speech tools which are trained into deep learning algorithms, vast datasets of human speech. Now, it can break down and replicate pronunciation, speed, emotion, intonation, as well, and there more accurate and natural sounding speech helps those with visual impairment, language barriers, reading disabilities. There are music creation tools which you can use to write short melodies or riffs, suggest or add instruments, compose a new song, create a soundtrack for YouTube or Instagram videos, mix match. You can mix and master and publish streaming platforms. Then there are audio enhancement tools as well, which can identify specific sounds, add or remove unwanted sounds like, for example, DScript or Audo AI. There is also going to be video tools, video generation tools which you can use like runway, which can transform video into new styles. It uses text, image or video as input. Now, there is also Es US, where you can upload photos or use text prompts to generate videos. Then these video tools can record a narration, enhance the audio, convert the file format. They can publish a video as well, and there is tools like Synthesia which can create custom Avatars. There are a lot of different audio and video generation models which you can use and tools which you can use for generating AIs generated videos and audio. 10. Tools for Code Generation: Hi, guys. Welcome to this session. In this session, we'll talk about various tools which we can use for code generation. So code generation models generate code based on national language input. Based on deep learning and NLT, these models comprehend context and produce contextually appropriate code. Now, the capabilities of these code generators are that they can generate a new code snippet or a program. It can predict code lines to complete partial code. They can produce optimized versions of existing code. They can convert code from one programming language to another. They can generate summaries and comments for code. They can also recommend programming solutions to solve a specific problem. Similarly, in this open AIs GPT as a coding generation model, Excels in human like text generation, it demonstrates immersive code generation capability. These coding capability of GPT are longer and more accurate codes can be generated. Coding can be done to develop apps, websites or plugins can generate code for images. So if you look at, for example, when we go on Chat GPT specifically and we write, let's say, write a Python code to generate a message to greet a person, so we can get a code like this, which it provides. Plus, it gives you the explanation of how it works specifically. Also, you can convert the same code into another language as well in this particular manner. Now, with respect to looking at coding with Gemini, it offers code generation in more than 20 programming languages. It provides step by step and detailed understanding of how to generate the code. There are certain limitations of Cha PTI and Gemini for coding as well where it cannot generate large or complex codes. I can I can understand programming and syntax, but not semantics. So their knowledge is limited to the data used for their training. Like, for example, they get outdated with new releases of frameworks and libraries. For example, knowledge of GPT 3.5 is limited up to September 2021. So therefore, other tools like GitHub co pilot can be used, which can generate code for various programming languages and frameworks. It is powered by OpenAI's Codex and develops solution based code. It is trained on natural language, text and source code. It can integrate with other code editors can produce code adhering to best practices and industry standards. There are other tools like poly coder also which we can use, which is an open source AI code generator based on GPT. It is trained on Github repositories, written in 12 programming languages and provides a library of predefined templates. It can create review and refine code snippets. Other than this, there is IBM code assistant as well, which is built on IBM watson.ai Foundation models. It can be integrated with code editors. It produces real time recommendations, auto complete features, and code restructuring. So these are all the various tools which we can use for code generation at this moment. 11. Generative Versus Agentic AI: Hi, guys. Welcome to this session. In this session, we wanted to understand the difference between generative AI and agentic AI. When we look at generative AI, they are fundamentally reactive systems. They wait for you to do something. Specifically, they wait for you to prompt them. And once you prom them, their job is to generate some kind of content based on what you have prompted, the prompt which you have provided. Now they are using patterns they learn during training. Right? So now things that it can generate, might be some text, it might be an image or it can be a piece of code, it can be an audio. So they have learned the statistical relationships between words and between pixels and between sound waves. And they have learned that from massive datasets. So when you provide a prompt, a generative AI predicts what should come next based on its training, but it works work does end at generation. So ideally, their work ends at generation. It doesn't take for the steps without any more inputs from your side. So it's heavily dependent on what kind of prompt are you going to give to it based on which it takes those necessary action. Whereas when we look at agentic AI, agentic AI systems, these are not reactive. They are proactive systems. Now, like a genetic AI, they often start with a user prompt, but that prompt is then used to pursue goals through a series of actions. And an agentic system basically goes through a bit of a life cycle. So the way this works is it kind of first of all, perceives its environment if you like. And once it's done that, it can decide an action to take. Once you decided that action, it can then execute that action. And then once that action has been executed, it can learn from that output and then go round and round all with minimal human intervention. Now, both of these AI approaches often share a common foundation. And that common foundation is the large language models or LLMs, which we call it. LLMs serve as the backbone for the chatbots, and yet there's actually other tools that are used for some of these generative things, diffusion models typically for images and audio. I hope this makes sense now. I hope you're able to understand the basic difference between how a generative AI operates versus the agentic AI. 12. What Are Large Language Models?: Hi, guys. Welcome to this session. In this session, we wanted to understand what are large language models. So this is going to the basis of these AI tools which we're going to look at today. So LLMs or large language models are basically advanced AI systems designed to understand, generate and reason with human language. So this is going to look into a massive amount of text data. They are trained on this particular data, which can be books, articles, websites, code, and much more. And they're able to predict and generate language in a human like. So that's the idea of basis of LLMs. The most striking part about this particular programming on this kind of language programming is that it is able to predict the next word or token based on the previous words or proms which you provided. It's going to look at the prom which you have given and it's going to look at all the historical proms which are provided by you and based on which it is going to predict the next word for it and provide you the output based on that. Now they're going to learn patterns in the languages in terms of grammar, meaning, context, which has been given trained to them and based on which the outputs are generated. Now, they use a deep learning architecture called transformer and based on which these models are built on, and they are able to give appropriate responses based on it. Now, another thing which is going to be the case is they also contain millions to trillions of parameters based on which also they keep that into factor when they are giving out these responses or based on the prompts which we have provided. Now, one striking piece about these LLM models, which you will see is the outputs can be random also. It might not be the case that you get the same output for the same prompt which you're providing. Let's try to understand what we are trying to say here. For example, if I just say Mary had a little. So we know where we are going with this. So if I just enter this as a prompt, it is going to give me a proper response based on the previous interactions, the data it has been trained on, so it knows the right output which it has to give. Similarly, if I say something like this. We know what would be the next line here. So it is going to look at that while it's a blue, sugar is sweet, and so. This is something which we are already aware of and the tool is also trained on and because of it, it is giving us the same output. But now you see if I say, again, if I give the same prompt, it is giving a little different output. Let's do it again. So you can see, it's going to give us various different outputs for the same prompt which we are providing. So the point being this that large language models are trained on huge amount of data with respect to hat GPT, specifically, it is trained up to 2021 data. And similarly, there are other language models which are much more newer in that fashion, like Claude is there as well and copilot, as well. So based on which, they are going to Google Gemini also. So they are going to be trained on the data from all of them coming from the Internet where all this data is provided from. And based on which it is going to predict it is going to predict the next word based on the tokens or words it has been inputed given on from the past. I hope this makes sense. I hope you understand the basics how large language models basically operate, which is what we are going to use a lot in this particular course. 13. How ChatGPT Works: Hi, guys. Welcome to this session. In this session, we just want to do a quick sneak peek into Chat JBT tool. Let's try to understand what is the potential of this particular tool, okay? So for this, you can go to the OpenAI website where you can access it. This is the website, the company behind hatGBT who have built out the tool. So you can come to this where you can come to products where you can go ahead and go to hat JBT Login. So where you can login and open an account with them, or if you have the account, you can directly access them and reach this page. So this is the home page of Chat JBT where you can start using it specifically. This is the chat column where all the previous chats will show up out here. If you don't want to see it, then you can just expand it in this particular manner and you can use it. So the tool is basically going to be where we can provide a prompt to the tool. And with the help of that prompt, the tool will analyze your prompt and give you the output, the results of it. So there are different versions of it right now, which is available. These are the ones which we can use, which is the latest version is GPT four oh, which you can see here, okay, which is very useful and very fast with respect to complex tasks which we are giving it. The other ones, the daily usage task can be done through four oh Mini, and there is the legacy model as well of GPT four. Now, there are multiple options which you get if you see the settings of the tool as well. So there are certain settings which you can set up over here, the general settings, how you want to look at the theme of it, the look and feel the theme of the particular tool can also be changed in this particular manner if you want to do that. Okay. Apart from this, certain personalizations which you want to do, you can do it as well out here. Now, the tool works in a very simple fashion wherein we can giving these prompts. So just to show you some example of what we can do, let's say, I have given a particular prompt, which is of planning an itinerary to visit Kashmir in India. So it's going to quickly give me all the particular day wise itinerary where how I can arrive to this place, what places I can check out, all those things, it will quickly give me. Now, based on this, let's say I want to see some images of the places to visit in Kashmir, so that also it can provide in this particular manner, which I can get an idea of that this is what I would be able to see in Kashmir. Also, what we can understand is, let's say, I want to know about different types of eating options which I will get. So that also it can give you the information here. If I want to see an image of any of the food, I can see that as well very quickly. And then if I am looking for any kind of fun activities which I want to do in Kashmir, then I can see some examples with images in this manner. So very quickly, I have a clear idea, more information about what all options do I have before I visit any particular city. And then finally, I'm also looking at the cost, the spend expenditure of visiting the place, so it can give me a rough idea of the flights, accommodation, transportation costs, meals, activities and sightseeing cost, all these estimated. So total estimated cost also I can get on for seven days trip or the number of days I mentioned. So this is a very valuable information which I can get now very quickly. Otherwise, what I would have to do is I have to do a lot of research on different search engines. To get this information, which can take up a lot of time. This is much more organized information, which I can quickly get right here. Another way which can be used for hat RPT is in my business where it is prose creation, I can give it a prompt like I want to know which I am a course creator on ii and I am looking for people who would be willing to which are the top performing courses which I can look at, which is of high demand right now, and people are willing to take those courses. So it can give me some prompts around that as well. So this way, there can be endless different opportunities or ways of getting information from this tool and different types of prompts which we can give, which can be useful for us, and it will give us organized information based on that. So I hope you are able to understand the potential of this tool, what all things it can do for us and give us solutions for various things which we are looking for right now. So in the coming videos, we will also see in depth ideas of different scenarios, situations where we can use this particular tool to get organized information, which can be of a lot of value. Thank you so much, guys, for listening into this, and I will see you in the next video. 14. ChatGPT vs Google: Hi, guys. Welcome to this session. In this session, we wanted to do work sneak peek into understanding the Google Gemini AI tool and also doing a quick comparison of it with Chat GPT. So let's have a look at this. So as you know, that Google has also built out their own AI tool, which is Gemini, you can search for it on Google and you can go to their website to open an account with them. So you can have a free version of it, as well as you can see here or you can also take the paid version, which is Gemini Advanced. So here, it looks very similar to Chat GPT. You can enter the prompt over here, and you can also upload any images, and you can listen. Microphone is also available out here which you can make use of. So here we can put the prompt. So let's see how the responses comes out in this case. In this manner, we can give the information. So now it is going to give us all the information about it. The good thing about it is the formatting is really nice where you can highlight the important information in this manner, and we can read through it very seamlessly. So that's a really good, nice thing about it. Along with that, they also provide an attached related content article which you can read through as well, which justifies with authenticates the content provided by the AI to. Furthermore, let's expand this further. Um, So now we can give an outline also of an article. Let's say we want to write an article so we can get some outline around it, it gives you some subheadings, as well. So information given in this particular manner, golden era, heroes, modern era, masters, and so on and so forth. So we can get that information as well out here. You can furthermore, use this information and we can convert this into an article as well. A So now we are asking to write the article. So here it is producing the article based on the outline provided above. So this way, we can get the information. So the information is pretty straightforward, simple. We can understand the language is really nice. You can see O legacy is a tale woven with gold, a saga of unparallel dominance that once defined the sport on global stage. So the language is very upmarket and very advanced and professional, which we get to see through the Google Gemini AI two. Let's try to compare the same prompts with ChangePT now, and let's see what kind of responses we get there. So we're going to use the same proms. So we're asking the same prom, it is going to give us the information, so we can see it's using the similar kind of information, which is obviously the same person which we have seen out here as well, which it is giving us right now. Let's see the other prompts also. So now it's giving us an outline for an article over here, similarly, the introduction Dancheno Bulwsing it's now picking up the specific players and their specific specialities and their history that is being shared out here, which is pretty good. Very specific information. Whereas if you look at CHAT GPT, it is going a little bit more generic information about the evolution of hockey, Indian hockey in the last years, in the decades. So this is more precise information which we get out here. Let's look at the article as well. So now, a So now we're asking to provide an article as well, so it is giving us that information. So good thing is, it's again, creating a structure in the article, like an introduction, then talking about each of the particular important players in this particular manner, we get to see. Whereas in case of the Google Gemini, it gives an overall information about the whole era and the topic which we're covering out here. Here, the article is more structured in terms of under picking up on each of the special players and talking about them. So overall, if you see the experience with both of them is decent. Personally speaking, I find Chat GPT much more specific to the point Chris and giving us more accurate information in terms of the particular information which we are looking for comparatively. I hope this makes sense. You understand now how both of these tools are going to work out for us. In the coming videos, we will have particular section where we are going to dedicate them only to looking at how Chat GPT works in different scenarios. Then we'll jump into Google Gemini scenarios as well where we'll see how that tool can be used. Thank you so much guys for listening into this and I will see you in the next video. 15. ChatGPT Interface and Layout: Hi, guys. Welcome to this session. In this session, we'll see the Chat GPT layout and the interface, how it looks like to everyone. So once you log into Chat GPT, this is how the interface is going to look like. You can see on the top left, we can see a left panel over here, which you can unhide and you can see all the details. Or if you want to hide it, you can hide it in this particular manner as well. So this is going to be a panel where you can see multiple things right now. If you look at the main page of it, this is where we are going to give the prompt to hat GPT and based on which it is going to give us the responses. Now the version of the Chat GPT, you can see over here as well on the top left, currently, I am a Chat GPT plus member, so I'm using GPT four right now, but you can see the other models as well available, which you can switch to also. From here, we can give the prompt and then you can move forward with it. On the left here, you will get the options to explore other GPTs which are created by OpenAI and the community which they have. You can come here and you can search for different GPTs which you would like to use and you can add it to your left panel and then you can make use of it. Other than this, you can also see the previous particular chats which we had done with Chat GPT out here. Idally if you click on any of these, you can certainly go ahead and have a look at it as well. In this particular manner, it will give you the responses over here. Now, once you get a response, there are multiple things which you can do with it. One is, you can certainly share this particular response with somebody. You can share that from here on the top right corner where you can create the link of it and you can share the link with your users with your friends. Apart from that, once the response is generated, ChaGPT gives you multiple options where it can read it out loud for you. You can make a copy of it so that you can use it somewhere. You can give it a thumbs up or thumbs down based on the response, or you can ask it to regenerate. That also options will come up out here. Now, in addition to this, if you want to go to a new chat, you can come up in this particular manner where you will get multiple options, which is like you can attach a file here and give it to Chat GPT to analyze it and then give responses based on that. You can also use the intelligence part as well where you can ask it to get into the think model where it thinks about your query, your prompt, and then response based on that. This is going to be search the web, so you can get it connected to the web as well online Internet and then research and give you the results based on the searches done from the Internet. Then there are other tools as well, which is integrated now with Chat GPT, which is Dali, which is a text to image generating AI tool platform, which you can use from here. Search again is available and think which we're looking at. These are all the options which you will certainly get out here with respect to four oh, which we get here. Now, in addition to this, what we are looking at here is if you can also see the plans over here, which plan we are in so if you want to upgrade your plans, you can do it from here specifically. Now, in addition to this, what we get to see is tasks which is coming up right now. You can start creating tasks as well, which you can give to Chat GPT, and it will be performing those tasks on a regular basis, regular intervals which you set it at for. Also, you can see your own GPT which you have created. If you've created a specific GPT for a particular purpose, they will get all listed in this particular section of the account. Now, customizing the GPT is going to be a case wherein we can tell what should HGPT call you? You can give your name. These are all inputs which you're giving about yourself, your interests, dislikes, and dislikes, which you can tell over here so that JAGPT now gives you responses based on your own inputs, your own personal inputs. What do you do? What traits should TAGVT have? All these things which you can enter over here? Plus, it gives you some suggestions you can add from here. Anything else? Chat GPT should know about you. You can give all that information, your background, your work related experience, everything you can enter over here so that now whenever the responses comes in, they come keeping all of this in mind. This is really great because this will really customize and personalize the responses for your work which you are doing. This is going to be the customization part. If you go to settings, then there are other things as well, general settings which you can change the theme of the look and feel notifications are there if you want personalization, which we talked about, speech as well. Data controls, you want to look at if you want to delete the account just in case Builder profile is going to be when you're creating a your own Chan GPT, how you want it to be shown to people, you want to name it in certain manner. You want to give your own website over here, you can give that as well. You can also get it connected to other apps if you want to. Which can be a Google Drive, Microsoft One Word or one drive or one drive work or school, you can connect it too so that you can pull up details from there very easily. With respect to security, you can see a multifactor authentication is enabled, that subscription, which is there, you can manage it, you can remove it, all that is possible. Now, once you click on the particular icon overhe, you come to the new chat right over here, and then you can give the chat specifically. In this particular manner. Now looking at that, Chat GPT is going to give you the response based on it, and then you can tweak it as well if you want to change it. All that will be possible. Now you can see you have got the response from Chat JPT. Now, if you want, you can again, go ahead and modify this as per your requirement. Now you can easily modify that and then you can get the response. Let's say you want a certain response, if you want to stop the response, you can stop it also midway. This way, the response will stop midway and then you can collect all the information if you want to. These are all the features of the tool which you will ideally get. You can also search for certain chats which you have done in the past. Maybe you can just search for it in this particular manner. And go to those chats very quickly in this particular way. You can use the search option as well. I hope this makes sense. You understand the interface, now, how the hat JPT interface is going to be for all of us. Let me show you the other models as well. If you're on hat GPT G four, the free version, it would be in this particular manner where you can use it. I hope this is clear to everyone. Everybody understands now the interface and the UI, the layout of hat JPT. Thank you so much guys for listening to this and I will see you in the next video. M. 16. ChatGPT Plus Features: Hi, yes. Welcome to this session. In this session, we wanted to just check what are the plus features, which Chat JVT offers in their model. So once you're on the tool and you're on the plus feature, there are a couple of additional things which Chat JPT is giving. The first is obviously going to be the intelligence part. You can use more intelligence. So here, Chat JBT will start thinking more and give you more accurate information. So this is something additional which you get in the plus feature. So let's have a look at this, how it is going to work out. In this manner when you give a prompt, it will start thinking about the response it needs to give discipling, so you can see, and then it will give you the response. This is going to be a feature which really helps to get more accurate information results based on which you can go ahead and use it for your own work. This is really good, which you can certainly use out here. Apart from this, the additional features which you can see here is, you will be able to attach files of different kinds out here, which can be a code, which can be images and then you can ask TragiPT to analyze it and give you responses based on that. Let's see some examples of this. Let's say we want Tragic PT to go ahead and debug a code, so we can give it a code in this particular manner and we can prompt it It's going to look at the image specifically and try to analyze what's wrong with the code and then give us some debugging steps. You can see it's also giving us a recommended code as well in this particular manner. This is one of the features which is there available. Other than this, let's say you want it to go ahead and decipher or simplify a complex image. We can look into that as well. So let's say this is the image which we are giving it and we want it to explain the image, civicle we've given this image and we're asking it to explain it in simple manner. So now it's given us a simple description of the image also in this particular way. These are additional features which you're seeing, which you get in a plus version, specifically speaking. Also, if you see out here, um, the additional things which you will get in this is going to be the code part. Apart from the free version, all the other things are available in the free version, but in the paid version, specifically, you will get the code part where you can ask it to write a function or simplify any code. You can help me learn Python. There can be a lot of ways you can ask it to write a code as well. Now it is going to go ahead and do that for us as well. You can see it's given us a Python code over here. This is the additional pieces which we will get with ATGPTPlus. I hope this makes sense. You understand now the additional features of the plus version of the tool. Thank you so much guys for listening to this, and I will see you in the next video. 17. Tokens and Context Windows: Hi, as. Welcome to this session. In this session, we want to talk about hA GPT tokens which you get to see over here. Tokens are you can consider large pieces of words which being used and counted over here. When you give a prompt specifically, the tokens are generated and hGPT different versions have different limits, token limits out there. For example, hAGPE 3.5 had a token limit of 4,096 tokens, and ChaGPT four later on had 8,000 plus tokens. And now that we have new versions of it, they are much higher number of tokens which we get over here. How it works is whenever there is a prompt which you give to hat GPT, the prompt will take some of the tokens from there. Let's say you give a really long prompt to hat GPT 3.5 wherein it uses up out of 4,096, it uses up 4,000 tokens. Now we are left with only 96 tokens for hat GPT to respond back. You input and hat GPT output both are considered in the total token amount, the limit which we have got here. That is why you might see certain times when you are having a long conversation with hat GPT, at the last stage of it, the responses might not be that accurate, might not be that sensible information which you're getting. In such a scenario, the hat which you can think of is starting a new chat. Or what you can do is you can go ahead and summarize the complete conversation, ask hat GPT to summarize the whole conversation in a concise manner, and then copy that into a new chat and start from there again so that you have the fresh number of tokens again generated for the new chat. So there are also different ways you can figure out how much tokens a particular prompt will take up. So that also we have tools like a tokenizer with tool which you can use over here. So first, let's look at how Open AI defines tokens on their platform. Tokens can be thought of as pieces of words which they have. You can see one token is almost approximately equal to four characters in English, one to two sentences becomes around approximately 30 tokens, one paragraph, approximately 100 tokens, and so on and so forth. Here you can read about the token limits, token pricing, even exploring tokens. Here you can see, every particular word gets a specific token. For example, M is three triple six. Color is 312, four, then red is 2266. Now, if you look at period, period is 13, which remains the same everywhere. Second one as well period is given as 13. However, if you look at red in lower cases is 2266, whereas red with upper case is 2297. Like this, it differs and this is how you can see tokens are used up in our prompts. Now, if you want to calculate a particular prompt, we'll take up how much tokens. You can use tokenizer over here. You can see this particular sentence will take about seven tokens characters are 28. If we pick a bigger text, let's say we are picking up this big text, In that case, it's taking 81 tokens and characters are 371. Each of them have been color coded now in this manner, you can understand. This is the idea behind tokens which needs to be taken into consideration. Whenever you are using CHAPT for different reasons, keep this in mind at the back end of your mind so that you are aware about it and you can optimize accordingly so that you get better responses. Thank you so much guys for listening to this, and I will see you in the next video. 18. SearchGPT Feature: Hi, guys. Welcome to this session. In this session, we want to talk about the search GPT feature, which recently Chat GPT launched. SarchPT is a particular feature which uses Bing to provide live information from the Internet and gives you all the updated data. It activates the real time needs. Search GPT detects when your question needs current information, for example, news or weather. It will retrieve data via Bing. It gathers reliable data from Bing, summarizes multiple sources into one clear answer. It also provides you with links. Each response includes links so you can verify the information very easily. Location use is also there wherein general location data is based on your IP address so that the Chat GBT responses are tailored according to that. Also, you look at the availability of it, the hatGPT Search GPT feature is available for GPT 40 users on plus or Pro plans. Search GPT is optimized for general data. It lacks hyper local info and is also only available for GPT 40 users. Privacy is still priority over here. Now, when you look at what are the new features in search GPT, you can see it's real time information. It pulls latest data from the web for up to date data answers. It summarizes the responses, gives you clear concise answers instead of giving a listing links. Also, the sources are transparency. It cites the sources with each answer for easy verification. Contextual follow ups keeps context, allowing natural follow up questions and flexible formats, it can present data in tables, lists or bullets for easy comparison. So let's have a look at this GBT feature on Char GPT two. So once you're on Chan GPT, we are on Char GPT 40 mini version. You can see this is the search, the web option which we get. Now here, you can go ahead and search for any information. Let's say we are saying RichelObama, now it's going to be searching the web, it will look at different articles and based on which it'll pull up the information from there. Now you can see it has also given us some recent news on the topic as well. So we can see different articles from here as well. The sources are provided. So if you want, you can see the sources here as well from where they have gone ahead and collected the information. This is really great because it then verifies the information for us from creditable links and that authenticates and gives more credit to the information which the Chan GPT tool is providing us. So this is how we are going to use the search GPT feature recently launched on Chan GPT. Thank you so much guys for listening to this and I will see you in the next video. 19. What is Prompt Engineering: Hi, yes. Welcome to this session. So in this session, we'll talk about prompt engineering. Understanding prompt engineering in detail how this actually works on the Chat GBT tool. So what is prompt engineering? So let's read through this and understand it clearly. Prompt engineering is a process of designing and optimizing prompts used in natural language processing models such as hat GPT or virtual assistant. This involves crafting prompts that are clear, concise, and effective in elicitating the desired result. For example, prompt engineering is making an effective fishing lure, just as well designed lure is more likely to catch the fish. A well crafted prompt will also more likely to give us the desired results. There are three main principles of prompt engineering which you keep in mind while you're working with this tool. The first can be being specific. The more criteria you give, the more focused the output will be. The more specific information we are going to provide to the Chat GPT tool, it is going to give us much more properly desired, structured responses based on that. Work in steps. So we have to break down a task into smaller chunks of task which we give it. We can't go ahead and ask ChaGPT to write a book for us. So we have to structure it down into small, small steps. So maybe discussing about the topic of the book, what will be the topic of the book? Then thinking about the table of content. What will be the topics, Chapter one, Chapter two. What will be the chapters for it? Then working on each of the chapters one after the other. Working in steps really helps to get a much more better responses from the two the other thing which you can keep in mind is iterate and improve. So once you get a response from Chat IPT, we can rework on the inputs as well which we are giving. Plus, we can improve on the outputs which Chat JBT is providing us. We can go ahead and modify that. We can ask in a different manner. We can bring out different versions of the output which we have got and ask again to improvise on that. All those things has to be a continuous process. So this is how your prompt engineering is going to evolve and improve over a period of time. Now, what makes a good prompt? Great prompts all come down to the data the model was trained on. Chat GPT data, which is at the back end which they have been pulling up, it's all based on the data they have pulled up and now based on that, it's giving us the responses. It's parameters, good prompting. Since we can only control one of these, here's what the good prompting looks like. So the good prompting, we have to keep in mind clear and concise language. That is direct and unambiguous. Whatever prompt you're giving to the tool has to be very clear and concise to the point vague prompts will produce vague responses. So we just need to go ahead and keep that in mind. The persona that you're assigned to hat GPT, also known as who it will be acting as in the prompt, there can be one aspect of it. We'll talk about it as well where you can You can ask CHAPT to act in a certain manner, like a philosopher, maybe a doctor or an engineer. So in that manner, you can ask HAG to act in a certain manner and give the responses. The other thing is the information and the examples that you provide, also known as your input. The more example, specific information you're going to give in your input, the responses will be that very well. High quality responses you will get. A specific task that you're requesting CHATPT to complete, also known as the desired output. We have to make sure that we have to ask for a specific task so that only then we can expect to get a desired result out of it. Refinement as needed once you receive your first response, also known as reeration until receiving the desired output. This is again, refinement of the outputs which we are getting and again, asking in a different manner to get better outcomes from ChargV. Now, main prompting steps, what you can keep in mind is defining the problem or goal in a clear manner, clear articulate what you want GBD to help you with using relevant keywords and phrases. In the prompt, you need to input the most useful industry and topic related terms into the prom to get the desired result, write the prompt. Crafting a concise fromm that clearly communicates the information and task that is required to be performed by the tool. Also, apart from this testing, your evaluation process iteration process has to be a part of it. Generate responses with Ctrip. Once you get the responses, you evaluate the results. You go ahead and iterate on it and ask for improved, you modify that and ask in a different manner to tragibty to get the desired responses. This is what is going to be prompt engineering. How you give your prom to the tool, which is going to define the kind responses you will get from it. I hope this makes sense. You understand prompt engineering now. Thank you so much guys for listening to this, and I will see you in the next video. 20. Intuition Behind Prompts: Hi, guys. Welcome to this session. In this session, we want to discuss about the intuition behind the prompts. So when you start giving the prompts to the LM models or the tool, the intuition or the pattern which you're trying to access from makes a lot of difference. So depending on what prompt you're giving and what kind of references the tool has off it from the past data makes a lot of difference. So whatever prompt you give each and every single word, whether there are whether it was common and it has a lot of pattern in the past or not, will make a lot of difference to the kind of output you are going to get out here. So it makes a lot of difference that the intuition behind the prompt is very clear, and that is going to define the kind of response you're going to get from those prompts. To give you a simple example of what we mean by this. So let's say I give a simple prompt to had GPT, where I say to complete this story, which is Mary Had a little. Now this particular phrase Mary Had a Little is a pattern which is well known, which is well known, and possibly across the Internet, there are a huge amount of content around Mary had a little lamb and the whole poem is there. So a lot of references are there and which the tool has been trained on. So it has a lot of data about it already. And because of which, it is going to give you responses in the same manner because those data points it has been trained, it is fitted into it, so it can retrieve that data and give you some information about it. So this will be very specific to that data it has been trained on. So you can see this pattern is extremely common common and well known and repetitive across the board. Whereas if I give a particular prompt, which is complete the story, a girl named Mary had a microscopic. Now, when I do this, when I add microscopic, this becomes very specific. Possibly the number of patterns around this, the tool is not trained on. The tool is not trained on, it does not have those many references of it. A girl named Mary is generic, possibly it has a lot of references for that, but microscopic will be something which is very specific. In this case now, since it has no such references, it is going to build on that and try to generate the next word. As the tool is trained on, it's going to look at the word and create a story around. As you can see here. This is how we want to make sure whenever we are giving any prompts to these AI tools, what is the pattern? Is there a pattern in the prompt which you're giving? Is the pattern well known or very specific? That is going to define the kind of output you're going to get out of the tool. So keeping this in mind makes a lot of difference because that is how you would be able to customize the tool to give responses according to your requirement. If you are dealing with a specific scenario where you want a specific solution, then we need to give prompts where the pattern is well known and we're looking for a desired output. But if we are working in a particular project where we want to look what is possible, what are the possibilities and there are new things we want to experiment with, then maybe the pattern which we want to follow is very specific. We can give some rare words, unique words like these, which does not have much references from the past, and the tool can just provide new ideas around that. I hope this makes sense. I hope you understand how we need to look at prompts and the intuition behind it and how we need to choose our words which can define the outputs which we get out of it. 21. Everyone Can Program with Prompts: Hi, guys. Welcome to this session. In this session, we wanted to understand that with Chat JBT now, everybody can go ahead and program with prompts. What we mean by this is that you can train the tool to give response as per your requirement. Now, this can be really useful and that is how you can say that an ideal assistant works. Wherein you give certain specific training and you want a certain kind an output from your assistant and based on which it is going to give you those responses. So now everybody can just simply give those prompts to program Chat GPT, or any other AI tool to give responses as per your requirement. To see this practically, what we mean by this is. Let's say I'm giving a first, I'm setting up some expectations with the tool wherein, I'm saying that whenever you generate output, turn it into a comma separated value list. That's a expectation setting which I have done, which it acknowledges, and now I'm giving my data point. Where I'm saying that my name is Tami Das and I'm teaching a course on generative AI for HR professionals. So now that I set this expectation earlier, it is giving me the response in that particular fashion. So now when it gives me this, I want to tweak this. I want to change this and give more rules to Cha GBT tool to get trained on. So I'm saying that from now on, the columns of the comma separated value list should be name, course, and role, another setting expectation. So this also it will keep in mind, and then it is going to give me the output. So it automatically gives me. So it does not the great part of this is I don't have to provide the data point once again. It has already taken that into consideration, and now straightaway jumps to the output, which is it takes the particular columns as name, course, and roll, and gives me that output correctly. So this is really great. It is getting programmed. The tool is getting programmed or trained on the different rules or expectations you are setting with it. In addition, again making some changes where I'm saying that in addition to whatever I type in, generate additional examples that fit the format of DCS felist. Now, again, I don't need to provide examples myself. It is automatically creating those examples in that same format. In that same format which I'm providing here. So now you see by following all these steps, we have now programmed the Chat GPT tool to give response in a certain manner. Now, when I give a simple prompt like this, it straightaway gives me the output in this particular manner because by now, it's already trained. It knows that it has to consider these three columns. It has to provide the first output, then give additional examples as well. So all that comes in together in one go. So you understand how the tool is going to work, wherein if you want a specific kind of an answer or output for your business, for your work, the tool can be programmed. Anybody can program the tool as per their requirement by setting these expectations, giving these rules, and then you start your work, give your prompts, and get the desired outputs. 22. Prompt Priming: Hi, guys. Welcome to this session. So in this session, we'll talk about prompt priming. So prompt priming is a concept which refers to the practice of providing some initial input to the model to the hat GPT tool before generating any kind of response. So this initial input really helps to guide the tool towards generating a response that is more relevant and customized to you. So the user's intended input. So it is very crucial and important that whenever we are giving prompts to the hatGPT tool, we are giving some context, some context, some background of what exactly what kind of information you are looking for. Like, for example, without priming, let's say, I'm saying, where should I go on my next vacation. Now, this is something it's super generic. Now, hATTPT will find it extremely generic as a input given and will give a very generic response to it. It will give me all kinds of places around the world, okay, and information about that. But now think about it if I give some context behind it, okay? So let's say I'm saying, I would like to go on my next vacation. I'm going on a trip with my wife and kids. The location should be tropical. I would love to go to a beach. I would like a direct flight from my place to LAX, and I have a travel budget of $5,000. Where should I go on my next vacation? So now what happens? I have given some context. I've given some scenarios, specific things which I'm looking for, my interests, my likes and dislikes, all that I've given context of. And now because of this, the prompt will be the response will be far better, much more relevant and customized to my particular need. So this is what we refer to as prompt priming. Let's look at one more example. Let's say I'm saying, please create three potential titles of my new online course that teaches people how to use AI. Now this is again, super generic because Chat GPT is going to give me all kinds of titles possible, which serves this purpose. But now, if I give some context, where I'm saying that, please create three potential titles for my new online course that teaches people how to use AI. Here is an example of some recent course titles. Please emulate the style and the written format of these. Let's say I'm giving some context, my current courses names are video editing masterclass. Edit your videos like a pro, cinematography master class, the complete videography kind. Now when I give some context like this, the outputs will be far better. The tool will emulate the writing style in this particular examples which I've shared and will give me responses based on that. So this is how you have to keep this in mind that whenever you're giving a prompt to hat GPT, we have to give context information with it as well so that you get the most specific desired response out of it. 23. Root Prompts: Hi, guys. Welcome to this session. In this session, we wanted to understand the concept of root prompts which these AI models have. So usually what is going to happen is they will have some basic root back end prompts which are being fitted into them, which sets the ground rules around how the outputs are going to come in. So it makes sense for us as well to identify and set up these ground rules for getting a specific kind of response from. So you can use the air tool in such a manner where you can train it to have these ground rules keeping in mind whenever they're giving out any kind of output. Maybe you belong to a specific industry and you require responses customized to that industry. So you can feed in those information into the tool so that it will keep that in mind all the time whenever it's giving any type of responses. So this really helps to customize the solutions as per your requirement, and there are higher chances of reaching the solution much faster. So just to give you a practical example of what we are referring to, let's say we take an example where we are setting the ground rule with the AI tool where we say that you are my personal assistant. Whenever you provide output, please make sure that you're giving the most time efficient recommendations, only recommend things that will save me time. Do not suggest things that do not save time. Okay? So these are my expectations, and you can see it says updated saved revenue, memory. Okay? So what it's doing is at the back end, it's making it saved in the memory section that this is how the responses should come out going forward. So now let's take an example. I say that I need to go for grocery shopping. What would you suggest I do in order to buy my groceries? If you see every answer which it is going to give now will be with that particular ground rule in mind, okay? Like fastest option, order online and home delivery. Saves time, okay? Reordering past items, two to 5 minutes total, it will take. So no travel, no cues. So again, referring to the same point that it is going to save us a lot of time. Okay. If you must go physically, minimum time required, you can open a Notes app, make a strict list which you want to buy. So there is no other things which you're shopping. Go to the nearest store, not the cheapest one. Okay, saves you a lot of time. Pick up pick items in one pass, right? You self checkout or card, UPI saves you time, leave immediately. So you see now the responses are all going to cater around that one expectation which I've set with the tool. Similarly, let's say another scenario, I need to buy a new car. What would you suggest I do? Okay? So in this also, it will keep that in mind, short list only two cars. Okay? One aggregator, which you can filter by budget, body type, and full stop at two options. Me is equal to wasted time. Okay? So keep referring to the point that we need to save time as much as we can in every response. Lock the budget and EMI. So you can see the responses are going to be now completely customized around that one set expectation. So setting up these root proms beforehand, before using the AI tools helps a lot in getting much more customized solutions to our queries, which is going to effectively resolve a lot of issues much faster. 24. Prompt Size Limitations: Hi, guys. Welcome to this session. In this session, we want to talk about the prompt size limitations. So as we understand the AI tools are developing over a period of time, so the prompt size limitations are also increasing. It is not going to be the previous ones like 3.5, 4.1 with AGBT versions. Right now we are sitting at Tra GBD 5.2. So these prompt size limitations have also increased. However, keeping this in mind, it still does not make sense that we are going to dump all possible information to Chat GPT and just ask it to analyze and come up with solutions. So just to give you a background about how it has changed over a period of time. So currently, if you see when GPT 3.5 started off, it had approximately 16,000 tokens it could take into consideration. And then once GPT four come into picture four oh, these numbers increased. Right? So over a period of time, this has become much more better. So when we look at specifically with respect to, let's say, the current ones, which we have, GPT 5.2 also has a specific prompt size limit, which is very high, which is approximately 400 K tokens which we can give, which basically means you can paste very long documents, which can be entire books, large code bases, long legal contracts, all these can put in easily without breaking them up. So that way the tokens, the particular limits, the prom size is going to operate. Having said this, the idea, the right way of doing this is going to be if you have a huge document which you want TraGPT to go ahead and analyze and give you solutions for a better way of doing it rather than dumping the whole document on the tool is going to be picking on the specific sections of the document. Picking up on the specific sections of a document and giving it to Cha GPT to summarize to bring out the essence of it or putting it into different pointers, finding out a solution for it. So that way, you will be able to make use of the tool in a much more effective manner. So then what you can do is, let's say you have 1,000 word document, you can pick specific segments. Let's say there are five segments of that document, you can pick one by one and you can ask Cha JPT to summarize and then you will have five different summaries of it, which you can put together in a concise manner, again with the help of Cha GPT, and then you can use that for your project. So that will be the right approach which you should be using when you are dealing with huge amount of data and you want Cha GBT to analyze it. So the basic point being this that if you have a huge amount of data, you can figure out which is the most important part of that particular data, which is going to get you the right output. So you have a specific task to complete to do that particular task. Which aspect of that document is the most crucial one which only you can provide to CHAGPT to analyze and get the solution out of it. I hope this makes sense. This is going to really help you because then what is going to happen is you're using the tool in a very effective manner, going to the crux of it and understanding what is the main area and which specific information is most valuable for HAGPT to get you the right responses. M 25. Introducing New Information to the LLM: Hi, guys. Welcome to this session. In this session, we'll understand another approach which you can use with these LLM models, which is going to be introducing new information to them. What is going to happen is a lot of the information it has been provided with has been provided to a certain date time, right? So now because of which it has a lot of information which is trained on, but we cannot say it's a complete information which they have. So there can be a lot of information which they are not aware about. So the great part is that when you are using these tools, we can add those information. We can introduce them to those new information, and the tool will automatically take that into consideration when giving out the output. So this is going to be really powerful because then you can use it in various formats. So, for example, if you're working it for your business, so you can give background about your business. You can tell about how many employees you have, what kind of products do you sell, what are your winning and losing products. You can give a lot of information and then ask your give your problem statement. So it will take that information which you have given into consideration when giving Yoga solution. Similarly, you can provide reports, you can provide data analysis. You can provide surveys from the past. You can give information about your customer's behavior. There can be a lot of information which you can give from your end to the tool and then it is going to take that into consideration and provide you the output as per your requirement. Give you a practical example of what we are referring to here. Let's say I give it a prompt, just a prompt which says, going back to the previous example that how many birds are outside my house? Now, tool cannot practically give us an output for this. So it's giving us a short answer, which is I have no idea, it's early morning and giving me a basic wing, it does not have enough information to give us an answer for this. Now what I'm doing is I'm giving it some data points. Let's say I'm saying that historical observation of average birds outside my house has been January was 120, February, 150, and so on and so forth. I've given it some data. So it's going to take that into consideration and now it is coming up with the output that, since we are in January, so it's going to be around 120. So now because of this information which you have provided it, it has picked on it and giving us an output solution for that. Now, if I build on this, let's say I build on this and I give more information, let's say, my house is covered by a glass dome. Now animals can go in and out. All animals live forever inside the glass dome, and then I give the question. So it is going to take that into consideration again. So you can see it says, this turns it into a logical problem, not a predictable problem. Okay. Let's restate the constraints here. The house is under sealed glass dome, okay? So like this, is going to take the additional information into consideration to carve out a customized solution or a response for your prompt. So the idea is that from here, what we need to understand is when you're using the tool, you can provide your information which you have in place. And as a supporting document as a supporting resource, which it can refer to, and then with the help of it, it will provide you the desired results. I hope this makes sense. I hope you understand the strategy, how you can use the tool in a very effective manner by providing all these additional information from your side. 26. 30 Simple Prompt Starters: Hi, guys. Welcome to this session. In this session, I just wanted to share some simple prompts which you can keep handy with yourself. Maybe you can stick it up on your computer, on your system somewhere, which can easily help you in getting some information very quickly from charge. So let's have a look at this. These are some 30 prompts which I had outlined over here, which are concise, simple proms aimed at inspiring you and getting quicker information. And this is how it is going to be wherein maybe, let's say, define the following term and give a metaphor. Elaborate on the purpose of something, create a template for something, construct an outline for this podcast. Help me create a budget for things which you want. Suggest some creative writing prompts to get me started. Brainstorm ten ideas for improving the writing of the transcript. Draft a well thought of chapter list for a book on, let's say, a book you're writing. Some recipes using these ingredients. These are some 30 prompts, which you can take a print out of and keep it with yourself and use it whenever need be. I hope this will be really useful because then you can get your responses quicker. You don't have to think much, you can just look at this, write it, and get the responses out very quickly. Thank you so much guys, for listening to this, and I will see you in the next video. 27. New Ideas and Copy Generation: Hi, Dice. Welcome to this session. In this session, we'll see some of the practically useful everyday prompts which we are going to look at and practice them and see them on the tool, how it's going to work for us. So these are going to be prompts which are going to be useful for our daily work and ideation. These are designed to provide a practical prompting framework for individuals seeking to quickly enhance their productivity and creative output. So these are some of the ones. The first one we are going to look at is the brainstorm new ideas, where we have created this formula, wherein we say that I am looking to explore a subject in a particular format. Do you have any suggestions on the topics I can cover? So let's take some examples of this. I am interested in creating an Instagram page that covers travel. What ideas do you have on topics I could include such as budget friendly destinations and hidden gems to visit? Another example can be, I'm working on a newsletter that focuses on technology. Can you recommend topics that would be engaging for my audience, such as the latest gadgets and software upgrades? Let's see this in action, how this is going to work out for us. Let's say we are taking this particular prompt and use it on hat GPT and see what kind of response it gives us. So now it's going to look at the prompt and give us the information. So budget friendly destinations, hidden gems, okay, which we can talk about here, local food guides. It's giving us travel challenges, travel hacks, solo travel stories, sustainable travel. These are all the different types of the page ideas which we are getting now, which we can explore. And now you can deep dive into it. So let's say you want to explore more on solo travel stories, you can ask Tat GPT to expand further on that. So this is how we can make use of these prompts very quickly and get the desired results. Other example which we can take over here is copy generation, which is basically another prompt which we have created where we are saying that I'm interested in a type of a text that highlights the benefits of a particular subject. Now please write a number for me on that subject. Now let's say the example can be I need a email campaign that showcases the features of my new product. Can you write one for me on the ease of use and affordability of the product? Another example can be, I'm interested in a website page that outlines the benefits of my coaching services. Can you write one for me on the personalized approach and proven results of my coaching program. Now we can see this also how this is going to work out. So it's going to give us the response. So it is taking information from previous chats as well and giving us all the information. Why choose our coaching program? Personalized strategy for your business. Proven success with real results, expert, guidance, ongoing support, and optimization, achieve sustainable growth. Okay, ready to master your ads. So now it's giving a call to action as well by the end of it. Very effective, very structured way of giving us the response, which we will be expecting. So these are the kind of daily prompts, guys, which you can start looking at. In the next video, we're going to see some more such practical daily everyday prompts which you can make use of. 28. Client Emails and Bulk Writing: Hi, guys. Welcome to this session. So continuing with the previous video, let's look at some more different scenarios of practically everyday prods. Another scenario can be of client and customer support. The prompt formula which we have come up with is, I wanted to act as a customer support assistant who has a particular characteristic. How would you respond to a text as a representative of our type of company? So example, I want you to act as a customer support assistant, who is analytical? How would you respond to a customer who has experienced a bug while using our software as a representative of our tech start? Or another example can be, I want you to act as a customer assistant who embodies confidence and empathy. How would you assist a customer with a billing issue as a representative of our financial services company? So let's see some examples of this. So let's say we're taking the first one. Now you can see it is writing the answer for us over here and it's asking for the specific information regarding the bug, exact error message, version of the software. All the required information is asked out in the email. Similarly, let's look at other scenarios. Another scenario can be generating analogies. Analogies can be really useful when they're complex topic and it's difficult to understand the concept. Such cases, an analogy really helps to simplify the topic and understand better. The prompt which we're using out here is, I'm trying to understand the concept of a particular concept, which helped me better understand this concept by creating a practical and easy to understand analogy. For example, I'm trying to better understand the concept of photosynthesis. Please help me better understand this concept by creating a practical and easy to understand analogy. So let's take this example. Another example is, I'm trying to understand the concept of search engine optimization. Please help me better understand this concept by creating a practical and easy to understand analogy. So let's take the first one and see this. So we're trying to understand the concept of photosynthesis, so here it is breaking it down. In this particular manner. Break down the photosynthesis into using that's simple to understand. Imagine your plant is like a solar powered factory. The analogy is they're looking at as a factory. The factory's job is to make food, but instead of using electricity, it uses sunlight. Here's how it works. Now it's giving you an analogy with a factory to explain the concept of photosynthesis. This is really great because this is going to simplify a lot of complex topics to understand at every sphere of work. Another practical example prompts can we guys bulk copy creation? So the formula which we're using here is, please come up with a number of content for a type of content for a platform that includes some references. So for example, please come up with eight email newsletters for my investment site that includes industry reports and data analysis. Please come up with four video scripts for a marketing YouTube channel that includes expert opinions and insights on digital marketing trends. So let's look at the last one So now it's going to give us four video scripts. You can see the video script is given with particular segments, which is the narrator, intro, body. All of that is given Section two as well, conclusion, then Video two. Complete specific video script with the structure being provided and the particular role plays are also mentioned very clear. So this is how these everyday proms are going to be really useful in understanding in getting some work done, which will be very productive for our business. I hope this makes sense. You understand the concept of everyday prompts, practical proms which you can use. Thank you so much guys for listening to this, and I will see you in the next video. 29. Modifiers for Better Outputs: Hi, is welcome to this session. In this session, we want to see how we can make use of modifiers to make our prompts better. There can be different types of modifiers which you can use here like qualifiers, words such as some few, many, all, they really help to give more specific insight into the prompt. Adjectives also which can describe describe or modify nouns and pronouns, they can also help a lot, such as red, happy, large, exciting. When you say, you want to want Chat ZIP to write a blog which is exciting, then it will understand exactly the tone in which it needs to provide the response. Similarly, adverbs, verbs which describe words which modify the verbs, adjectives or adverbs, such as quickly, well, loudly, intensifiers, which you can use over here, which can be extremely, totally negatives are very good to use because these modifiers will really help to negate all those words or sentences which you don't want haziBT to provide you, which can be never to. You add those in your prompt so that hat JPT does not give responses with those particular terms. Number words which you can use as well, it's much better to give a particular specific prom than a generic prompt. Like for example, you can give a prompt to hat JPT which can be, can you list down the top ten movies in US? Or you can say, which is a very specific prompt versus asking which are the best movies to watch in US. Giving number words can be really useful to get very specific information. Other than that, you can also look at time words, words that indicate when something happened or will happen. If you're asking for specific information about when did the US independence happened, you can use those particular prompts, modifiers over there. Place words such as here, there somewhere would be really good to use because that also becomes very specific. Degree words totally completely slightly. These are some things which can really help to get very specific information from JAGP the intent is understand this thing guys. The choice of modifiers really helps to enhance the quality of responses which you get from it. The idea is the main idea would be that whenever you're writing your prompts on Chat GPT, give it some time and thought around how you want the response, what kind of response you are really expecting from Cha JPT and then formulate your prompt using all these modifiers to get a very customized specific information, which can be of really good use for you going forward. 30. Few-Shot Prompting: Hi, guys. Welcome to this session. In this session, we want to talk about a type of prompting style which is short prompting. Short prompting is basically a concept wherein when you're giving your prompt, you can give some kind of context to the prompt as well to get more specific information. Now in this, there can be three levels. The first level is going to be zero shot, which is, as you can understand by the name itself, wherein you're giving a prompt with no context whatsoever, no context, no data, no guidelines which you give to hat GPT, and now hat GPT has complete free hand to give you information from all directions. The second one can be one shot where you're giving one piece of data or guideline to Cha GPT, and based on which the Chat GBT will produce the response for us. And the third one which you can also use here is few shot prompting where you give multiple pieces of data or guidelines because you are expecting a very specific kind of information from Cha GPT. Then you can do a few shot. For example, in a realize scenario, a zero shot prompt can be write a YouTube script for my tech review channel. Now this is so generic and so basic, it can go in whichever direction possible and Chat GPT is going to give you all kinds of information here. One shot can be using this example one as a reference, write a YouTube script for My tech review channel, and now look at few shot. A few shot will be using these examples one, two, and three as reference, write a five minute YouTube shot on the latest iPhone camera specifications for MtechRview channel. Now we have give becoming more specific because there are some requirements which we want to fulfill and based on which we want to see the response. This is called a short prompting technique which you can also make use of. 31. Tabular Format Prompting: Hi, guys. Welcome to this session. In this session, we're going to talk about another type of prompting style which is tabu format. You can also get responses in a tableau format from HAG PT with this particular type of prompting. This is going to be a way wherein you're going to give a series of prompts to Chat GPT, and it's going to give you the information in that particular format. This allows Chat GPT for clear organization and presentation of data, making it easier for users to analyze, understand, comprehend the output. The formula is going to be where you're going to give the question first, and then you can give second prompt. Once you get the response for it, you can give a second prompt, which is what are the different categories you can break your answer. Into for more descriptiveness. Now, you get a little deeper into it and you get a response related to that. Once you get that response, then you give your third prompt, which is now create one table that includes your original answer with these categories separated into different columns. So this way, the whole information gets transformed into a tabular format. Let's see this in action how this will look like. Let's say we're taking the first question, which is what are the main factors of growing our YouTube channel? The first is we are just doing a initial prompting with no other additional things to it, so we're getting the information. Already, this is in a point by point *** given to us. You get the information. Now, what we do is we can do the second prompt asking it to break the answer into more descriptiveness. Now you can see it's getting more descriptive over here. Once you have this output with you, you can ask for the tableau format for this information. It's going to give you all the answers in the tableau format, specifically with this information out. And that would be much more easier to understand, comprehend and use as well. So you can see here it has gone ahead and created that for us categories subcategory description, In this particular manner, the whole table has been created. This is the tableau format of prompting, guys, which you can also use to get your information in certain format. If you are very comfortable with Excel and data, you want to do a lot of data analysis. You can ask Chat GBT to give you the output in that particular format and then it becomes much more easier for you to work on that. Thank you so much guys for listening to this, and I will see you in the next video. 32. Chain of Thought Prompting: Hi, guys. Welcome to this session. In this session, you want to look at another type of style of prompting, which can be chain of thought prompting. Chain of thought prompting is a simple technique wherein you can ask CHAIPT to explain the answer in a step by step format. Rather than jumping to the answer straightaway, you want hATIPT to take you through the complete steps to reach to that answer. Now it's going to work on that and give you a step by step understanding of how it reached and came up to that answer which you got. So this way, the understanding is better. Sometimes when we are interested in a particular topic, we would like to know the process, how the particular thing was evaluated. So in such cases, this kind of response is very useful. For example, the format, the prompt formula which we can use is you can give your question and then you can just say, let's think step by step. Now Chat GPT will give you the solution in a step by step format. Like, for example, what's the diameter of the sun? What is the weight of an oxygen molecule? Let's see this in practical how this will make a difference. So let's start with first without our prompt and see what response at GPT gives us. You can see simply we have jumped to the answer and it has given us the answer very clearly, which is there. But now let's do it step by step. Now you can see it has gone step by step where it starts with understanding the sun's size. The sun is a massive ball of hot gas and gives clear understanding definition of the sun's size. Now what is a diameter? It's also defining what is the diameter as a unit to measure. Then measuring the sun's diameter. It's looking at now they're coming to the point where they are trying to look at sun's diameter how to measure. They're giving that understanding. Then sun's diameter, based on these observations, diameter is 1.3 million. They come up with the figures which they've given and finally, they're concluding it with the final labs. This way, they've broken it down into multiple parts, defining each part, and then joining them all together to come to the final conclusion. This really helps. Let's look at another one. Let's go with the question first. What is the weight of the oxygen molecule? Now, in this case, what is happening is it is automatically taking the previous conversation into consideration and giving us the output in a step by step format. This is what we were expecting by the step by step prompting methodology. Wherein is telling us the oxygen molecule. Composition is what mass of the oxygen atom is this much, then converting the atomic mass units to kilograms, it turns out to be this much. Now we're getting all the information in a very step by step format. I hope this makes sense. You understand this type of prompting which you can also use to understand better the responses which you get, understand the whole process, how ChatGPT processed the whole information and give you the solution. Thank you so much guys for listening to this and I will see you in the next video. 33. Ask Before Answer Prompting: Hi, Ayes. Welcome to this session. So in this session, we'll talk about another type of prompting, which is ask before answer. This is a technique where you guide HAGBT to ask for clarification before giving an answer. This really helps to ensure that the model answers are much more accurate and as specific as possible. So the formula which we use here is the first prompt which we give is we tell ChaGPT that you are an expert in the field of the industry. I'm going to ask you some specific tasks to complete, but before you answer, I want you to do the following. If you have any questions about my task or uncertainty about delivering the best possible answer, always ask bullet point questions for clarification before generating your answer. Is that understood? This is the first prompt which you give. Once you give that and Chat GPT acknowledges it, then we move to the second prom, which is great. My question is, your task is this, please ask any questions you have so that I can improve my prompt before you complete your task. So this way, now it is going to ask you the relevant questions, and then you can answer those questions to get a very customized, accurate, specific information. Let's see this in action how this will look like. The first thing which we are going to do is we're going to give this prong, the first prompt. Let's say we are talking about an industry which is consult. Now it understands it has acknowledged it, and now we give the second prompt. So now based on this, it's going to ask us the questions. You can see target audience, who is your ideal customer for consulting? Current strategy, what marketing and sales strategies are you currently using? Consulting poker, what is the main area of consulting you offer? Goals, what are your sales targets for next six to 12 months? Branding and positioning, how do you position yourself in the market? Budget and resources, what budget and resources are available for marketing efforts? Sales funnel, do you have a structured sales funnel? Now it has asked us all the relevant questions which we can answer. We can start answering it one at a time, target audience, You can go ahead and give the rest of the answers in this particular manner, give all the answers. Then once you give your answers, it will take those answers into consideration to give you the most customized response based on that. I hope this makes sense. You understand this technique which is asking before answering prompting, which you can also use with tra gibt. 34. Effective Prompt Revisions: Hi, guys. Welcome to this session. In this session, we wanted to see how we can also improve the revisions or the prompts or the outputs which we get from Chat GPT and put it across in a much better format. The best part of Chat TPT is going to be in contrast to any search engines which we have the conventional search engine like Google. Chat TPT possesses the memory capacity, which basically means that it remembers the previous conversations which we had and based on which it can give you customized responses. Now, once you get any responses from Chat GPT, you can go at an further follow up on that and then you can improve those responses. These are some of the ways by which you can do that. So for example, once you get the response from CHGPT, you can ask hATJPT to put the single most important keywords in bold formatting so that we know which other important keywords in that response. You can ask it to organize information by date, location, price. You can ask ChaJPT to come up with more novel and uncommon results, possibly. You can ask it to provide a appropriate images. Let's say you got the information in a coin by point format, and now you want it to have respective relative Imoges as well. Chat GBT can do that for us. Also, you can ask it to explain the whole response in a way of a level of a 5-year-old so that he can understand. Other things which you can do is you can transform the whole prompt, the whole response into a tableau format. That is also possible. You can ask you can ask AGBT to rewrite the whole thing from the perspective of an industry expert. You can ask it to write it in a formal or informal manner. You can ask them to fix the grammar or any find and replace. You want to replace certain terms from the response, you can do that as well. You can ask it to add some personality, some humor to the whole content. I can do. Uh, apart from that, you can ask it to write this from the perspective of or in the voice of your favorite author or a personality celebrity. It can transform that in that fashion. So you can see there are a lot of things which we can do. You can also ask it to summarize the whole thing in one single tweet. You can ask it to expand this to three part summary. Okay. So all the responses you've got can be modified into multiple different ways. You can ask it to compare and contrast the most important information. And then you can ask maybe to just list down all the best topmost, ten key takeaways from it. So other thing you can do is you can ask it from an expert point of view. How would you improve it further? Then putting it across into a bullet point list. There are so many things which you can do a revision of of your responses which you get from Cha GPT, which can further enhance and improve the quality of information you're collecting from it. I hope this makes sense. You understand this concept of prompt revisions, which you can also do with Cha GPT. 35. Randomness in Output: Hi, guys. Welcome to this sessions. In this session, we wanted to understand the randomness in output which we get from these AI tools. So we need to understand the fact that with the AI tools like Chat GPT, the responses, what you will get from the tool will not be the same all the time. And we saw this in the previous section as well that the output is going to be different all the time, and that is how the tool has been trained to provide responses for. The intent of the whole thing is that we want to try out and see different types of responses. So that is how the tool has been built and trained and given data. And that is why every time when you see the responses are going to be very different from each other. Now, that is how it is going to operate, and we need to somehow accept it and live with that and work towards that only. That is the current state of these LLM models or tools which we have where the output is going to be different from each other. They can be constrained within a specific section of responses which we're getting, but they will not be identical. Responses will always be a little different from each other and that neu answers will be there because that is what we want to see with the AI tools, the intent is always that we want to see unique responses, something which we have never thought of, and that is what has been ingrained into the tools, and that is why the outputs are always random. So just to give you a simple example of how this is going to be, let's say, if I give a prompt to Chat GPT where I say that how many birds are outside my house. Now, this is a very open ended question which I'm asking without giving much of information. This is going to give me one type of response where it's obviously saying that I don't have a way to see outside your house. Okay, if you want to quick estimate, it's giving me some certain steps that look and count method, sound method, photo method. There are various ways it is helping me count and figure out the solution myself. So that is one solution, one response which it is giving. Now if I give the same prompt once again, again, it is first of all, accepting that it can do it. But if you want the number, you'll have to look, listen or share a photo. Another kind of an output. The first one was steps given to figure out myself. The second one is I can share look and listen or share a video or a foot. Same way. Now, if again give the same prompt, it's going to admit that it can't do it, and right now the number of words outside is unknown. It's just giving me the answer that unknown, it does not know until I look into it and show me. Okay. So this is how the responses are going to be wherein the outputs are going to be random for the same prompts which we give. Now, this is not a technical glitch. It is the way the tool has been built out and trained for these randomness. Now, there's a pro and a con for this as well. So when we are trying to figure out things and we are trying to build something, and that time, this randomness or different types of responses really are helpful because then because we are running our ideas and we want to see something different, so possibly that can be really useful. If we are in a situation where it's a research work going on and you want specific answers or solutions to do that research work, then this random output might not be that much useful, okay? The only thing the tool can do possibly is to stay within the realm of that particular topic and give you responses. It's not going to be arbitra really vague responses, but he is going to stay within that domain and give you responses within that domain. That is how we need to start accepting the tool is going to behave and work with it in our favor. 36. Fill-In-The-Blank Prompting: Hi, yes. Welcome to this session. In this session, we'll talk about the fill in the blank prompting style, which you can also use. This is a format which allows the user to focus on a specific aspect of a sentence or idea and encourages deeper thinking. So let's look at the formula itself, what we can use out here. So we will start with one prompt first, which is going to be where we tell chat GPT that you are an expert at creating prompts that generate the most concise and resourceful responses. What additional bullet point details can I add to the following prompt to improve the output? My prompt is you give you a prompt and then once you get the response, based on that, you again give the second response, which is second prompt, which is great. Now turn these bullet points into a fill in the blank format which I can put my information into. This way, what we are doing is we are trying to get more relevant prompts from Cha JBT. We are asking Chat GPT itself to give us some more relevant prompts, which I should be asking HAGPT too and then getting better results out of it. Let's see this in action how this will be. The first thing we are going to do is we're going to give this prompt. The prompt which you're using is, I have $100,000 in savings and what should I invest in? Now based on this, it is going to give me the questions, Are you aiming for short term or long term growth? Risk tolerance. Are you comfortable with high risk time horizon, preferred investment type. It has asked me those questions now. Now, based on this, I'm going to give the second prompt where I'm asking it to convert this into a fill in the blank format, which I can then fill up. Now it has given me the fill in the black format with examples as well. I can fill this up and this will become my particular information which I can use further to get better results. This is another type of prompting style, which you can certainly use with ChatGPT to get better results. 37. Perspective Prompting: Hi, guys. Welcome to this session. So in this session, we wanted to look at another style of prompting, which is perspective bomb prompting. Now here, what we're looking at is this framework basically helps to broaden your understanding and provides a more comprehensive view of the topic at hand. So now what happens is, for a specific topic, we are asking Chat JBT to provide different perspectives of how to look at that particular topic. So when it gives you that, you have a holistic information idea, and clearance about that particular topic. So the understanding is much, much better. So this can be done in two particular ways. One is a singular perspective. The other one is multiple perspectives. So singular perspective is you can give a prom, which is please write about a particular topic from the perspective of a particular viewpoint. That's straight and simple. The other one which you can do is multiple perspectives where you ask hagiPT to write an argument for or against the topic of the topic which you have from multiple diverse perspectives. So this includes the names, the point of views of different perspectives, such as the viewpoints as well. Let's see this in action how this is going to happen. So let's say we are looking at the first one with singular perspective. We want Chad GPT to write about kickboxer from the perspective of a kickboxing coach. So now it's going to give us a perspective of a kickboxing coach, improving as a kickboxer what all things can be done, perfecting your fundamentals, building conditioning, improving your defense, developing mental toughness, footwork and movement, incorporating sparing. You can see these are all suggestions from our kickboxing coach, right? Now, the same thing we can ask from a different perspective where we ask to give a perspective of a human anatomy expert. So let's see how different this is going to be. So from a human anatomy expert perspective, what is important is optimizing your stance and posture, engaging your core muscles, understanding the role and hips of the hips in movement, improving agility with ankle and knee, mobility, and so on and so forth. You can see how diverse perspectives can be there for the same topic. This can be endless. You can ask for different perspectives, and by the end of reading through all of that, you get a much better, deeper understanding of the particular topic you're addressing. I hope this makes sense. You understand this style as well. Thank you so much guys for listening to this, and I will see you in the next. 38. Comparative Prompting: Hi, guys. Welcome to this session. In this session, we'll talk about comparative prompting. So comparative prompting is as simple as highlighting the key similarities and differences across various factors, which help you to make much more better informed decision and gain a deeper understanding of the strengths and weaknesses of the two options. So here, what we do is we ask At GPT to compare and contrast the following text examples, outlining the similarities, differences, qualitative characteristics, quantitative factors, functionality, key takeaways, and other factors into one table. And then we give the two pieces of cont. Now based on which it will analyze it and give us the information in a tableau format for both the type of content. This really helps to make comparisons and understanding of both of them becomes much more better. Let's see this in action how we are going to do this. We're going to give the first. This is the first prom which we are giving where our content is going to be this. Now, it's going to put it into a tableau format, as you can see, business philosophy. Okay? We can see design philosophy, product strategy, brand image, innovation, all of that, which we can see out here now given to us in this particular manner. The same thing you can do with another example as well. Let's look at another example. Investing in real estate versus investing in cryptocurrency. Investment type, nature of investment, risk levels, ROI, liquidity, volatility, market dynamics, entry barriers. We can see now it has given us the differentiation between the two types of content with respect to the characteristics, the topics which we wanted to give us. This is really useful, easy to understand and digest, comprehend, and then we can make use of it in our business. 39. Reverse Prompting: Hi, Gins. Welcome to this session. In this session, we want you to see another style of prompting, which is reverse prompting. Reverse prompting or reverse engineering the prompt. So what we are basically talking about here is how you can go ahead and reverse engineer any piece of content to go back to the prompt which generated that content. So the intent over here is understanding the content which you receive, which you see right now, what prompt can generate that content particularly. That is what we are trying to reverse engineer over here. So we have come up with two prompt formulas which you can use out here for this particular purpose, wherein you can give the prompt and this will help to reverse engineer the content to go back to the original prompt which was given to get that content out. So if you see the first one is where we ask STIPT to act like a prompt engineer expert that is able to reverse engineer prompts based on the text that is provided to you. So we give this particular prompt first and set up the whole space stage for AGPT that it works like a reverse engineer prompt a prompting expert. And then once StraTPT acknowledges it, then we can give the particular text to it, and it will reverse engineer the prompt and tell us the original prompt which was given for that content. This is one option. The second option is prompt can be we are giving multiple different prompts to hat GPT to set up the conversation. Clearly, wherein we first initially say that let's talk about reverse prompt engineering. By reverse prompt engineering, I mean creating a prompt from a given text. Can you give me some simple examples of reverse prompt engineering? Chat GPT will give us some examples. Then we will say, can you create a very technical reverse prompt engineering template? What are we doing is we are priming the tool. Priming the tool specifically to have previous historical conversation data so that it understands reverse prompt engineering better. And then finally, we give the prompt, which is now reverse prompt Engineer, the following text, be sure to capture the tone, syntax, language, and writing style of the text. With these two different approaches, possibly you will be able to go ahead and reverse engineer the prompt and go back to the original prompt which generated the content which you have now. The intent of doing this is once you get the original prompt, you can use it on other products. So if you come across a really good content across anywhere, you can use ATGPT to reverse engineer and take you back to the original prompt which can generate it. Now that you have the original prompt with you, you can apply that on other products, your own products in your own business as well. Let's see this in action how really this is going to happen. What we're going to do first is look at the first option. We are going to go ahead and take the first prompt and give it to ChatPT. We will say the type of content is, let's say, a tech company. Product description. I understood. Okay. And then we will give the second prompt. Great the text, I would like to reverse engineer is, and we'll give the example from here. Let's say the example is this. This is the content which we have got hold of and what we expect out of ChachPTs give us the original prompt for this, which will generate this kind of content. You can see it has generated the particular prompt as well, which will help us to generate this content, itally speaking. This is one approach, which you can easily use out here. The second approach, let's have a look at that as well. In the second approach, we start the conversation with this where we say, it understands reverse prompt engineering, what it is. Then we ask Chat GPT to give us an example of prompt engineering. It will give us some example of prompt engineering, reverse prompt engineering. Right now, it is still giving us the result for the first prompt. Now we're asking the second one, asking for an example of a reverse prompt engineering. Now we are going to ask AratGBT to create a template for reverse prompt Engineering. We are priming the tool. We are giving a lot of data to hat GPT to understand from reverse prompt engineering because our intention is to ask it to create a particular prompt for the original content at the end. Now this is the final prompt which we want to give. You can see it is giving us the response for the third prompt right now. Now we can give we'll ask HAGPT to reverse prompt engineer the following text. Let's say this is a product which has a very high reviews, number of reviews, good rating already. We want to reverse engineer the prompt. We want to know the original prompt, which can generate this kind of headline. We can reverse engineer for this. We can reverse engineer for the description of the product right here, multiple things. Whichever things which is needed for you for your own product listing, you can ask it to reverse engineer and take you back to the original prompt. I'm taking the headline for the timing. I've given the headline. And now we are asking you to reverse engineer that original text it is taking. Now you can see it is generating the reverse engineered prompt for us. This we can use to generate this kind of a headline going forward. Now, once you have the original prompt with you, you can use it on any product. You can just change the product name over here and the style tone, syntax remains the same. But you can use it on any other product of your own for your product descriptions, and it will write in that particular style. I hope this makes sense. You understand the concept of reverse prompting now. Thank you so much guys for listening to this, and I will see you in the next video. 40. Constructive Critic Prompting: Hi, guys. Welcome to this session. In this session, we wanted to see and look at a different type of prompting style, which is constructive critique. Now what we want is that in this particular one, this prompt can provide objective and expert feedback on your writing, highlighting areas of improvement, and offer constructive criticism to help you refine and enhance your copy. So here the prom formula which we can give is we want Chat JPT to act as an expert and critique in the subject of your industry. Now, we will want him to criticize our content, which is given and convince me why it's bad and give me constructive criticism on how it should be improved. For some context, so you give your product and service details of the purpose of my product is this, you give your content goal. Let's think step by step, and I want you to address each piece of content individually, and here is my content to critic. So now the whole idea is to get some feedback on our content from Chat GPT as a critique, and based on that feedback, then work upon it and make it better. So let's see this in actual how you can effectively use this. So let's say we are using this particular prompt, So after this, you can go ahead and provide your content which you have in place, and it was going to go ahead and critique that and give us all the particular feedbacks on it, which you can then incorporate. So this is also a really great way of prompting, which you can use so that you can have somebody who has much better knowledge about the topic or service and give you constructive criticism on that. 41. Prompt Patterns Overview: Hi, guys. Welcome to this session. In this session, we'll talk about the prompt patterns. So we understand now that when we are giving a prompt to LLM models like CHAPT, the pattern which we use in it makes a lot of difference in the kind of output which we get out of it. So if we are looking for a specific kind of an output, then we need to make sure that the pattern of the words choice has to be specific in that particular order. So that is going to control the kind of response which you're going to get from the LM models, the outputs which you are expecting out of it. This becomes crucial in any kind of task or work which you're going to do and you're using the LLM models or the tools specifically for a specific objective. Knowing the patterns properly is going to be crucial when you're using these tools. Just for an example, let's say, when I'm giving a prompt something like Mary had a little we know that we have a specific an output which we're expecting out of the tool. That is when we get this output which you are looking for. It becomes very evident that in order to get an output, which is the next line, it's freeze was white as snow, I have to make sure that my prompt pattern is in that particular format. For if I'm going to give any other particular output, possibly, chances are the output can be a little different. Like in this case, I'm giving it again over here, so it is giving us the same output. So you need to make sure that the patterns which we are choosing the choice of words which we are having in a prompt are very crucial and specific and u to the point so that it gives out the right output which we're looking for. That is why going forward, what we're going to see is different types of patterns in this course, which is going to give you outputs in certain manner. I hope this makes sense. I hope you understand now the criticality and the importance of having those specific patterns in our prompts which we give to these tools. 42. Persona Pattern: Hi, guys. Welcome to this session. In this session, we'll discuss about the persona pattern. This is one of the patterns which can be very effective, which you can use to make use of the AI tools, the hat GPT or LL models in a very effective manner. What we mean by a persona pattern is going to be a scenario wherein let's say we want a specific kind of an advice from an expert or let's say we want some kind of help or a response from a certain expert specifically, we really don't know what will be their response, how they are going to talk, and what information do they have. In such cases, for example, let's say, I want to get some advice from a dentist. So I don't have the expertise of being a dentist. So I would be approaching this person and provide my problems which I have, and I'm going to get a response based on their expertise, their experience, and they're going to give me the specific advice. So similarly, we can make use of the AI tool to behave in a certain manner, being a per being a tool of expert in a specific field and give us the output in that particular manner. We can ask the AI tool to act as a specific expert in a specific field and get those outputs. That is what we mean by a persona pattern. So the tool can behave in a certain various personas and then give us the response based on that. Let's see this in practical what we exactly mean by this. Let's say, I'm going to tell the AI tool to act as a skeptic so it needs to act as a skeptic that is well versed in computer science. So it has a knowledge of computer science, how computers work, and whatever I'm going to tell it, then it's going to provide a skeptical, detailed response based on that. So now it has accepted that it's going to respond as a computer savvy skeptic. And now we are going to say that let's say there is a concern that AI is going to take over the world. So this is my statement. So it is going to give me the answer with skepticism, which is AI is not an agent. It's a toolbox. When people call AI today, it's a collection of narrow task specific systems, classifiers, predictors, optimizers, and large language models. Intelligence is not equal to power or control. So it's going to give us all the information based on so now, if you change, you can also change these personas as per your requirement. So let's say, I'm going to say, again, that the salesperson at the local computer store is telling me that I need at least 64 GB of RAM to browse the web. So again, for this, it is giving me the skepticism because I have defined that. I've set that expectation that it needs to behave like a skeptic. So it's telling me that that claim deserves immediate skepticism because of technical grounds, it's almost certainly nonsense or at best wildly misleading. So you can see the tool is now trained to be skeptic, and it's behaving in that particular persona with a knowledge about computer science and giving us all the pointers around that. Let's change this and we can have a different persona altogether. Let's say, I'm saying that act as a 9-year-old skeptic. Now the persona is changing. This is a 9-year-old person who is skeptic and whatever I'm going to tell this person needs to respond in that same manner, keeping in mind that this person is 9-year-old. So when I say now AI is going to take over the world, it says, I don't think so. Like how would it even do that? AI is just stuff inside computers. It can't walk outside. It doesn't have arms and it can't even plug itself into the wall. You can see the difference in the response. In the previous response, this person had knowledge about computer science or had a lot of specific information to share. But now this being a persona of a 9-year-old skeptic person, you can see the response has changed accordingly. This is really effective. This is really powerful as a tool where you ask the tool to behave according to a specific persona and then get outputs based on that. Let's say I have a specific requirement with respect to marketing in my business or let's say sales or let's say HR. So I can ask the tool to behave like a experienced HR person or a marketing genius or let's say a sales maverick and give me outputs based on that. So I will get responses accordingly, and that is going to be really useful for our business. I hope this makes sense. I hope you understand now how persona patterns are going to work. 43. Audience Persona Pattern: Hi, guys. Welcome to this session. In this session, we'll talk about another prompt pattern which you can certainly use is going to be audience persona pattern. So we have spoken about the pattern wherein we ask HAGPT the AI tool to act as a certain persona and then give us the output based on that. Act as a researcher or marketing analyst or a director of a particular company. So that is the persona pattern which we had talked about. Now, here it is going to be about we want HAGPIT to give us a particular output for a specific kind of audience. So that is why this is an audience persona pattern which we are looking. So we're going to ask JAGPit sudden question and we would ask it to answer, keeping in mind a specific audience and then formulate the answer around that. So that is what we mean by an audience persona pattern. A simple example can be that let's say I want haJiPiT to explain how cricket as a game works to a 5-year-old kid. So now the audience over here is a 5-year-old kid. So the AI tool will try to explain the concept in keeping in mind the mindset of a 5-year-old kid and try to give us the output in that particular manner. Let's see a practical example of how this is going to actually work out. So when we come to ha GPT, we can give it a specific prompt. Let's say I'm giving it a prompt right now where I'm asking it to explain the large language models and how they work to me, or assume that I have no background in computer science. This is the audience I have defined here. Okay. So I have no background in computer science. I have zero knowledge about computer science. So keeping that in mind, the tool needs to explain LLMs to me and how they work for us. So this is what we mean by audience persona pattern, which you can also use wherein the tool will be able to give us the output, keeping in mind the specific audience it is catering to. So you can see now, so it is giving us the output over here wherein it says large language models are advanced prediction machines for words. It's making it very simple layman terms. It's explaining LLMs to a zero technical background person. What is LLM LLM is AIS system trained to understand and generate human language. Now, usually, this would not be the ideal definition which we will get for LLMs. We'll get much more technical definition which we'll get out of it. But since we have defined an audience over here in the first prompt itself, ChaGPT is customizing to it and giving us the output based on that. 44. Flipped Interaction Pattern: Hi, guys. Welcome to this sessions. In this session, we want to talk about another prompt pattern which you can certainly use is going to flip interaction pattern. This is going to a pattern wherein we usually are asking questions tool, the Cha JBT tool. But here, we're going to flip it and ask Cha JBT to ask us questions. Can be useful when we are looking for a certain answer, but we don't have much information about the solution, how to get to the solution. For that, we don't have enough information ourselves. In such a case, we would ask Chat JBT to ask us those relevant questions which we can answer too and based on which it will then be able to provide us the solution. That is what we mean by flipped interaction pattern where we flip the whole process of the AI tool asking us the questions and we provide the necessary answers based on which the final output is arrived at. Let's take a practical example to understand how this is going to happen. Let's say I give this particular prompt wherein I tell Chagp that ask me questions about fitness goals until you have enough information to suggest a strength training regime for me. When you have enough information, show me the strength training regime. Ask me the first question. The first question it's asking me is, what is your primary fitness goal right now and giving me all the options. I give him let's say fat loss and muscle gain. Second question is, what is your current body weight, height, age, and gender? I give the information. Then the third question comes in, what is your current training experience level? I provide that as well. Then the fourth question related to it comes, do you have any injuries, joint pain, or movement limitations? I provide information for that as well. Then finally, about your lower back, then it asks me further questions based on that. So like this, we can come to the final output, which will be a strength regime, specifically, a routine plan, which TajiPt can create for us based on all the answers which I give to its questions. So this can be really useful and helps us to find out answers for difficult questions. There can be a lot of questions, scenarios, problems which you might be facing professionally, where you're not able to reach to the solution clearly because you are not aware of all the information which is needed for it. There we are going to make use of this AI tool to get help in ways of questions it can ask us, the important questions it can ask us and we can provide the answers for it, which helps us in finally arriving at the main answer. I hope this makes sense. I hope you understand now how flipped interaction pattern can also be used in our prompt engineering with hagiPT. 45. Question Refinement Pattern: Hi, guys. Welcome to this session. In this session, we want to discuss about a different prompt pattern which you can consider is the question refinement pattern. This is going to be a pattern wherein we are asking Tha JBT specifically to refine our question. So we are proactively asking TajibT to look at our question and possibly suggest us a better question to ask. Now, this is going to be really useful because as you understand, the usage of AI tools is purely dependent on the kind of prompts which we are giving, and that is where also we are taking help of the ad. So this can be really helpful in getting the right answers, possibly, which we are not able to get with our own questions which we are giving as a prom to the tool. And that is where question refinement pattern comes into existence where we can make use of it. So the intent would remain that we are going to improve the quality of our question and then ask it to the tool so that we get better results. So this can be a pattern which you can prompt, which you can give beforehand to charge Bit to set the expectations. Wherein we say that whenever I ask a question, suggest a better question and ask me if I would like to use it or not. So here we are doing two things. One, we are obviously asking for AI's help to improve our question. Second, we are also asking it to give us the option of choosing whether we want to take that new question in hand given by it, or we want to go back to our original question. Let's see how this will work out in practical. Uh, so I give the prompt whenever I ask a question, suggest a better question and ask me if I would like to use it instead or not. They have updated the saved memory and confirmed it that it will do it. Now let's say I ask a question which is like, should I visit China? Now, when I give this prompt, frankly, this is a very vague prompt which I'm giving. Okay? There is not much clarity around the context of the prompt specifically, so that it does not have, still with that, GPT will try to improve the question and try to understand and give some context behind the question as well and give you a better question to ask. Which can be, is visiting China in the next one to two years a high ROI travel decision for me, considering cost, visa complexity, family comfort, and overall experience. Then it will give you the answer. This pattern, I would suggest everybody should be using where you set the expectation beforehand with HAGPT and based on which we try to refine our prompts. We try to refine our questions which we are giving to HAGBT to get better results 46. Cognitive Verifier Pattern: Hi, guys. Welcome to this session. In this session, we'll talk about another pattern which you can certainly use with hat GPT, which is going to be cognitive verifier pattern. So this is going to be a case wherein LLMs can be really useful when we are trying to ask them specific questions. Now, in order to improve the quality of our questions, we can prompt it wherein we ask Chat GPT specifically to divide our question into multiple other questions and then give us the final resolution. So this way, what is happening is we are taking the AIs help to improve the quality of our question by dividing into further more questions and then answering them in totality to get to the final solution or the answer which we are looking for. This is we call a cognitive verifier pattern which we can use. This really helps because what we are doing is we are breaking down our original question into different parts. So that gives clarity. That gives clarity to the question and the real answer which you're looking for. And because of which, the AI tool is much more able to provide a much better answer. This is the prompt which we can give to Chapit wherein we say that when you are asked a question, follow these rules. Generate a number of additional questions that would help more accurately answer the question. Combine the answers to the individual questions to produce the final answer to the overall question, right? So this way, we are trying to get a better answer by improving the quality of our question, and we are taking the AIs help to break down our question into multiple questions and based on which it gives us the answer. So let's see this in practical how this would be happening. So let's say we first set this expectation with AlgebD And now we can ask a specific question, let's say. So now this is going to be a little vague question which I'm asking. Okay. And now, based on that, it is going to give me certain questions. So if you see, to answer this specific question, these are the questions which AI has come up with, which is what city and climate you are in, right? So which makes sense, which is relevant to get the answer. What season is it right now? Is there standing water nearby, right? Rough size of your front yard? Is it urban, suburban or rural? Is it evening or night or daytime? Right? You can understand from the questions itself, these are not vague questions. They are absolutely relevant to find out the proper answer for the question we have asked. This is how we can use the prompting method also wherein we try to improve our prompt by taking help of AI tool like Cha Gibt where we ask the AI tool to subdivide our prompt into multiple questions, and then with the help of those answers from those questions, we finally get our overall answer. I hope this makes sense. Thank you guys for listening to this, and I will see you in the next week. 47. Recipe Pattern: Hi, As. Welcome to this session. In this session, we look at another pattern type which you can use is going to be recipe pattern. This is going to be a scenario wherein you are asking a specific question from the Chat DPT tool and you don't have the complete solution for it. You have part of the solution which you have in your mind, but rest of it, you don't know, and that is where you need the help from the AI tool to fill up that gap. That is what we mean by a recipe pattern, wherein we are looking for a specific solution for a problem, but you have part of the solution with you, but you require the AIS help to provide the rest of the solution. Okay. So let's see a practical example of how this is going to be useful. Let's say I am looking for a trip, specifically, I'm doing a trip from one place to another. So I want the AI tool to tell me specifically. Here I'm giving the prompt, which is we're going to add a feature. I will tell you my start and end destination. And you will provide a complete list of stops for me where I can stop including places to stop between my start and destination and have defined my start and destination places as well. So I am clear about what is needed, but I want the complete solution. I have part of the solution with me, but I'm looking for the rest of the information. So that is what CAPIT now does. Okay? So it's giving me areas where I can stop, okay? It's telling me why stop here for optional detour is being given. Okay? Then similarly, other stops areas which are being provided. Same thing. Now I can do wherein I can now use this as a training modle for other scenarios as well. So I can give a start And destination. So now it's giving me the particular stops which I can have for different destination. You can understand this is what we mean by a recipe model wherein you are looking for a solution, but you are not able to reach it because you don't have the complete process, how you will reach that solution. You have part of the solution with you and you're requiring AIs help to provide the rest of the solution for you so that we can get the desired output. That's our recipe pattern which you can also use on Chat JV. But 48. Ask for Input Pattern: Hi, guys. Welcome to this session. In this session, we want to talk about another pattern which we can use, which is ask for input pattern, which you can use as a prompt on Chat JBT. So this is a scenario wherein when we are looking for a specific kind of solution from Chat JBT AI tool, we define certain rules. Now, we define the rules and based on which we want it to give us the output, the result which we're looking for. Now, usually, what would happen is the moment you define the rules, it will give an output and will give you a list of information about the whole. Okay. That is what you don't want. What you want to do is you want the AI tool to take all the input, the rules which have been given and wait, wait for your input to come, your question to come and then give us the solution based on the rules which are defined. That is where we are going to make use of ask for input pattern. This is a pattern wherein you define the rules and you tell the AI tool specifically that keep these rules into consideration and don't give any extra information right now. When I ask for an input, that is when you give us the solution based on the rules provided. So that is what we mean by ask for input pattern. Let's see this in action, how this is going to be. I've given a particular prompt where I say that whenever I ask you to write a prompt for me to accomplish a task, list what the task is. List alternate approaches for completing the task and then write a prompt for yourself for each approach. So now I'm defining that it does not need to provide any other extra information apart from what I have defined over here. When you are done, ask me for the next prompt to create alternatives for. So now it has saved that into memory and now it is giving me to write to write a prompt to accomplish a task. I will clearly define the task list alternative approaches, write a separate prompt and ask you for the next prompt. So this is how we can make use of the ask for input pattern, which will primarily help us to control the AI tool from giving us overwhelming information and which can become difficult for us to manage later. So we are going to cut it short for it, and define the set expectations, define the rules, and also define how much information we want from it. And that is where this pattern can be really useful. 49. Few-shot Examples: Hi, guys. Welcome to this session. In this session, we want to look at another prompt pattern which you can certainly use is going to be a few short examples. Now, this is a prompting way where we're trying to train the tool to give us a specific kind of output. So how we do that is we give it certain examples. We give it a particular input and based on which and give him a desired output. So we give multiple such examples to the tool and we try to train. We try to train it to understand the kind of inputs and based on which gives us the correct output for that. This can be really useful where what you're doing is you're training the AI tool itself to give a specific kind of answer which is suitable for your own business, for your own self. So this is another type of prompting which you can certainly use out here. So let's take an example of what we are doing here. Let's say I give an input wherein I say that the movie was good but a bit too long. And the sentiment around that was the idea was, it's a neutral review which we are trying to give. Similarly, let's another input which I give is I didn't really like this book. I lacked important details and didn't end up making sense. The sentiment around this is negative. Similarly, I give an input, which I love this book. It was really helpful in learning how to improve my gut health. The sentiment is positive. Now I have given these inputs and the output to the AI tool to train it and understand where I'm coming from and what kind of output I'm looking for. Now I give a new input, which is, I wasn't sure what to think of this new restaurant. The service was slow, but the dishes were pretty good and I leave the output to be answered by the tool. So now, as you can see, the tool gives me an output which is neutral. This is what we mean by few short examples, which you can certainly use where you're training the AI tool to give us an output in a specific manner based on the kind of examples you have given it as to understand to make it understand where you're coming from and what is your expectation out of it. I hope this makes sense. I hope people to understand the various proms which we are trying to apply over here in AGPT specifically to improve the kind of results we get from it. 50. Few-shot Examples for Actions: Hi, guys. Welcome to the sessions. In this session, we'll see some other examples of few shot prompting, which is more catering to taking some kind of action. So we understood how we are able to use these kind of prompts to train the AI model to give us a certain kind of output. So that is what we're extending further here with looking at other scenarios where you can use this pattern, the few shot pattern and get different output, which can be more related to catering to different situations, catering to different actions to be taken in a specific situation. So let's see how we can use this in this specific scenario. Let's say I'm giving a specific situation. Situation is that I'm traveling 60 miles per hour and I see the brake lights on the car in front of me. Come on. The action should be, we need to stop down, stop there, so action is brake. Then I have just entered the highway from an on ramp and I'm traveling 30 miles per hour, so I need to accelerate. Then a deer has darted out in front of my car while I'm traveling 15 miles per hour and the road has a large shoulder. We are saying break and serve into the shoulder. Uh, another situation is, I'm backing out of the parking spot, and I see the reverse lights illuminate on the car behind me. So what we need to do. This is what I expect as an output from the AI. So it has learned the situation and action we are expecting and based on which it is giving me the output that we need to stop immediately and wait. So you can see we have now trained the AI tool to give us a specific kind of answer based on the situations provided. To extend this further, uh, we can ask the AI tool itself to give us more examples of situations and action analysis examples which we want to do. So now you can see it has provided those particular examples as well. Like for example, the traffic light turns yellow and I am ten feet from the intersection. Continue driving through safely, do not slam brakes. Okay? The traffic light turns yellow and I'm 100 feet from the intersection, then brake smoothly and prepare to stop. So like this, it is able to provide us various situations and actions as well. So this can be another use case of few short examples which you can use prompting, which you can use, which can help you to train the AI in a particular manner to give us our desired outputs. 51. Few-shot Examples with Intermediate Steps: Hi, guys. Welcome to this session. In this session, we'll see another scenario, few short examples which you can consider using when you're using when you're prompting the Cha GPT two. Here, what we're looking at a scenario wherein a few short examples show does not need to be only of two types where we're giving an input and we're getting an output, a situation action thing. Okay? So here, what we can also introduce are some intermediate steps, which basically means that when you give a particular situation, it can follow certain steps. It can think about certain scenarios and then come to an action. Okay? That can also be a possibility. So it does not has to be a short input output format. So you can train the AI tool in different ways. So we need to expand our mind and understand that we are trying to train the AI in different formats. This is one of those formats where just an input and output might not work, and it can be a tricky situation wherein multiple things needs to be taken into consideration and then the output needs to be provided. So here, we are going to include certain intermediate steps in between, and then the action is being taken. This is really going to be effective when let's say in a real life scenario can be catering to customer service, catering to customers queries. So you can have a train AI tool which can answer I can give different kinds of outputs, intermediate steps it can give to the customers and based on which it tries to tackle their queries and answer and resolve their issues. Let's see a practical example of what we are trying to say here. Let's going back to the same example, the previous example in the previous video we had seen. This is a situation we have given. Situation is I'm traveling 60 miles per hour and I see the brake lights on the car in front of me, come on, right? So I think now the intermediate steps is, I think I need to slow the car down before I hit the car in front of me, right? The action taken would be press the photon, brake now, again, I start thinking that the car isn't going to stop online. So the action I can take is check if the shoulder is wide enough to swerve into. So I start thinking the shoulder is wide enough. So the action taken is swerve into shoulder, right? Another situation can be I have just entered the highway from an on on ramp and traveling 30 miles per hour. So thinking I need to speed up to the speed limit so that I don't hit get hit from behind. So the action is rest foot on accelerator. So I start thinking I have reached the speed limit. So the action would be let up on the accelerator. Similarly, I can give an action a situation which is I'm backing out of the parking lot and I see the reverse lights illuminate on the car behind me. So what can be the action? So it is now trained. A tool is trained to give us the output in this particular format, so it starts thinking. The car behind me is also about to reverse. We could collide. So the action is immediately press the brake to stop reversing. Then I need to make sure the other driver sees me, right, that I'm thinking. So keep the brake pressed and honk lightly to alert them. So you can see now the Air tool is giving us the output in that particular manner, and it's getting trained the way we want it to think and give us outputs. We can also ask it to generate another example. So now it is generated another example, which is I'm driving through an intersection, traffic light turns yellow, I need to decide quickly whether it's safer to stop or continue through the interaction. So the action can be check my speed and distance from the stop line. Okay? Now, let's say I've given the specific action now. As you can see, the tool is getting trained, you can now deviate the conversation in whichever format you want. Like the last action is, let's say scan left and right while passing through and continue driving safely once clear. Then I say that let's say I'm running out of gas. So then what will happen? I'm driving and notice the gas is near empty, so I'm running out of gas, so the action can be taken. So you see this is another tend of format of f shot prompting which you can use where you are giving certain intermediate steps which needs to be taken into consideration before coming to the final output. 52. Writing Effective Few-shot Examples: Hi, guys. Welcome to this session. In this session, we'll see how we can write effective few short prompts as well on Cha GPT specifically. The intent of this particular session is to understand how sometimes when we are giving these few short examples of prompts to the AI tool, there can be certain mistakes which we make. In such cases, how we can rectify that and make our prompts better. So let's try to understand how this is going to work out. Let's say I'm giving a specific prompt right now, which is this, which is a few short prompt format, input, brick, output hard, input pillow, output soft, input car, and output now required, right? So in this case, the AI tool is giving us a prompt, which is going to be the car is fast. Now as you can see, what is happening here is based on looking at the prompting which we have done, the I tool is trying to understand what should be the ideal output, and it is giving us the output as fast. Now because of which, what is happening is, which is possibly not the right output expected output which you are looking for, and this is our fault. This is our fault wherein we have not given a good prompt to the AI tool. The main problem with this particular prompt is lack of information. We have not given context, we have not given extra information. What kind of an output are we looking for? That is what is missing. Which is why the AI tool is giving us an output based on whatever limited information or knowledge it is able to gather from the prompt we have provided. So that is why what we have to do is we have to. So we give the output that we are not looking for. We are looking for output only in soft and hard, okay. So then we have given some context that how we want the output to be. So then it is coming with the output the car is hard. Material wise. Okay? So now, again, what we do is, let's say we give it a specific prompt, which we have given out here, object is plane, speed is fast. Object worm, speed is slow, object is car, speed is fast. So you get the drill how we want the format to be. And here it is able to provide the right output. Now, again, what is happening is in these particular scenarios the Now, if you look at a specific scenario now, now we have given the object is ball. Okay? Again, a vague context which we are giving out here, ideally speaking, okay? It is not going to be again, ball can be fast. It is giving an output right now as fast, but it can be slow as well, a ball which is being played by a kid, so it can be slow. So all those things possibly can happen. So the idea is that whenever we are giving few short prompts, we have to also make sure that the format is fine, but the content of the format needs to be enough information, context has to be provided properly, and then only we can expect the right output. You have to give enough information, context around how you want the output, and then we can get the desired results. 53. Thank You For Taking This Course!: Hi, guys. I wanted to congratulate you for coming to the end of this class. Thank you so much for taking this class. I hope this was useful. We're able to learn the strategies and implement it in your business going forward. I look forward to seeing you soon in a new class, guys. Thank you, guys.