{"id":23226,"date":"2025-03-03T09:45:27","date_gmt":"2025-03-03T08:45:27","guid":{"rendered":"https:\/\/performance-msg-life-sk.rucolabs.sk\/?p=23226"},"modified":"2025-08-25T14:07:37","modified_gmt":"2025-08-25T12:07:37","slug":"podcast-6-umela-inteligencia-v-praxi-tipy-nastroje-a-bezpecne-vyuzivanie","status":"publish","type":"post","link":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/podcasts\/podcast-ai\/","title":{"rendered":"Podcast #6: Artificial intelligence in practice &#8211; tips, tools and safe use"},"content":{"rendered":"<p><span class=\"TextRun Highlight SCXW36422820 BCX8\" lang=\"SK\" xml:lang=\"SK\" data-contrast=\"none\"><span class=\"NormalTextRun SCXW36422820 BCX8\">In the next episode of the podcast &#8220;Na vlne kodu&#8221; (in Eng. On the Wave of Code), we were inspired by our listeners. We dive deeper into the world of AI with data scientist Michal Bystricky and system administrator Jakub Novak <\/span> <span class=\"NormalTextRun SCXW36422820 BCX8\">from<\/span> <span class=\"NormalTextRun SCXW36422820 BCX8\">msg<\/span> <span class=\"NormalTextRun SCXW36422820 BCX8\">life<\/span><span class=\"NormalTextRun SCXW36422820 BCX8\"> Slovakia. Listen and get <\/span><span class=\"NormalTextRun SCXW36422820 BCX8\">valuable tips on how to use AI effectively in practice and how you can make it your ally instead of your competitor.<\/span> <\/span><\/p>\n<p><iframe loading=\"lazy\" style=\"border: none; min-width: min(100%, 430px); height: 150px;\" title=\"Artificial intelligence in practice - tips, tools and safe use\" src=\"https:\/\/www.podbean.com\/player-v2\/?i=xr6kv-1811893-pb&amp;share=1&amp;download=0&amp;fonts=Arial&amp;skin=f6f6f6&amp;font-color=&amp;rtl=0&amp;logo_link=&amp;btn-skin=7&amp;size=150\" width=\"100%\" height=\"150\" scrolling=\"no\" data-name=\"pb-iframe-player\"><span style=\"display: inline-block; width: 0px; overflow: hidden; line-height: 0;\" data-mce-type=\"bookmark\" class=\"mce_SELRES_start\"><\/span><\/iframe><\/p>\n<p><span data-contrast=\"none\">The AI era is already here, and it\u2019s advancing continuously. It\u2019s clear that we will encounter it more and more often, and it\u2019s up to us to decide whether it will move us forward and open up new possibilities or leave us standing still. Artificial intelligence can help us save time and energy for the things we really enjoy. Today, we\u2019ll take a look at some useful tips on how to use AI tools effectively. <\/span><\/p>\n<p><span data-contrast=\"none\">Our invitation was accepted by data scientist Michal Bystricky, who specializes in language models and trend prediction, and system administrator Jakub Novak, who uses AI daily to optimize processes and avoid overload. Listen to the episode titled <\/span><b><i><span data-contrast=\"none\">AI in Practice <\/span><\/i><\/b><b><span data-contrast=\"none\">with our HR manager Ivana Hricova or read the transcript.<\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal, how would you explain to someone who doesn&#8217;t know much about AI what it actually is?<\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal:<\/span><\/b><span data-contrast=\"none\"> I see AI as a simplified human brain because I see a lot of similarities between the two. The latest models can already selectively forget irrelevant information and, like us, only remember important facts. In late 2024, Google introduced in an article <\/span><i><span data-contrast=\"none\">&#8220;Learning to Memorize at Test Time&#8221; <\/span><\/i><span data-contrast=\"none\">the next generation of Titans, also known as Transformers 2. The innovation lies in the fact that these models learn not only during training, but also during test time <\/span> <span data-contrast=\"none\">(inference time) &#8211; that is, at the moment when we interact with them.<\/span><\/p>\n<p><span data-contrast=\"none\">This means that if we ask the AI model to be stricter, for example, it will remember that and be stricter the next time it responds. This process is now built directly into the model, so there is no longer a need to use external memory management applications, making it more flexible and able to adapt to new situations. <\/span><\/p>\n<p><span data-contrast=\"none\">Another fascinating thing is the way the models store information. New research shows that this AI model learns better when something surprises it, much like humans. When it comes across unexpected information, it remembers it faster. The researchers are thus trying to replicate the way our brains work &#8211; the more cues we have about an event, the more deeply we remember it. <\/span><\/p>\n<p><span data-contrast=\"none\">AI also learns to gradually forget irrelevant details so that it doesn&#8217;t get lost in the mass of information. The paper also describes that memory is part of a neural network and the new models have three forms of memory &#8211; short-term, long-term and persistent, which allows them to select relevant data and better respond to new situations. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Jakub, what is your opinion on the matter? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> I would explain it more simply. To me AI is still not at the level of the human brain, although it is moving towards that. Developers are using principles we already know from nature &#8211; when something works in the biological world, they try to apply it to machines. We do this in car manufacturing, in aircraft, in systems optimization, and now in artificial intelligence. So to me it&#8217;s still trying to get closer to that brain, but it&#8217;s still an online simulation of something that the brain is supposed to replicate. <\/span><\/p>\n<p><span data-contrast=\"none\">If I had to describe AI to someone who had never heard of it, I would say it&#8217;s like having a personal assistant who can help with almost anything, from writing to solving technical problems. It&#8217;s not perfect, but the more effectively you use it, the more time and energy it will save you. <\/span><\/p>\n<div class=\"inside\"><div class=\"blog-quote\">\n    <div class=\"blog-quote--wrapper\">\n                <div class=\"blog-quote--content\">\n            <div class=\"top\">\n                <svg version=\"1.2\" class=\"topquote\" baseProfile=\"tiny\" id=\"Layer_1\"\n                     xmlns=\"http:\/\/www.w3.org\/2000\/svg\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\"\n                     x=\"0px\" y=\"0px\" width=\"200px\" height=\"141.111px\"\n                     viewBox=\"0 0 200 141.111\" xml:space=\"preserve\">\n                    <g>\n                        <g>\n                            <path d=\"M37.335,92.175c-4.4,11.067-11.333,22.001-20.601,32.535c-2.934,3.334-3.333,8.134-0.934,11.867\n                                c1.867,2.934,4.934,4.534,8.267,4.534c0.934,0,1.868-0.067,2.801-0.4c19.601-5.733,65.403-26.067,66.67-91.271\n                                C94.004,24.305,75.604,2.704,51.669,0.237c-13.268-1.334-26.468,3-36.269,11.8C5.6,20.905,0,33.572,0,46.773\n                                C0,68.773,15.601,88.042,37.335,92.175L37.335,92.175z\"\/>\n                            <path d=\"M158.075,0.237c-13.201-1.334-26.401,3-36.201,11.8c-9.803,8.868-15.401,21.535-15.401,34.736\n                                c0,22,15.602,41.269,37.335,45.402c-4.399,11.067-11.334,22.001-20.601,32.535c-2.934,3.334-3.335,8.134-0.935,11.867\n                                c1.867,2.934,4.936,4.534,8.268,4.534c0.933,0,1.867-0.067,2.8-0.4c19.602-5.733,65.404-26.067,66.67-91.271v-0.934\n                                C200.01,23.771,181.81,2.704,158.075,0.237L158.075,0.237z\"\/>\n                        <\/g>\n                    <\/g>\n                <\/svg>\n            <\/div>\n            <p class=\"quote-perex\"><span data-contrast=\"none\">&#8216;AI is a tool that can assist you with almost anything. It&#8217;s not perfect, but the more effectively you use it, the more time and energy it will save you.&#8221; <\/span><span data-ccp-props=\"{\"134245417\":false,\"335559738\":240,\"335559739\":240}\"> <\/span><\/p>                    <\/div>\n    <\/div>\n<\/div>\n<\/div>\n<p><b><span data-contrast=\"none\">So, you&#8217;re saying that AI is inspired by the human brain in that it can learn through use, retaining important information while forgetting irrelevant details. However, AI is still far from being as complex as the human brain, although developers are increasingly applying its principles to make it work more efficiently. Right? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal:<\/span><\/b><span data-contrast=\"none\"> I would follow up on what Jakub mentioned when he said that AI is just an online simulation. What if the human brain is also a form of simulated intelligence? The entire universe, including us, operates based on the laws of physics and chemical processes. Human intelligence is the result of neural connections and chemical signals, which we only partially understand so far. What if it too is just a biological simulation? Why do we think ours is the \u201creal\u201d one? Maybe we are just preoccupied with our own subjectivity and experience. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b> <span data-contrast=\"none\">This is getting a bit too philosophical for me, haha! It&#8217;s eleven o&#8217;clock, and I&#8217;ve got a long day ahead of me. I&#8217;d hate to fry my brain.<\/span> <span data-contrast=\"auto\">\ud83d\ude0a<\/span><\/p>\n<p><b><span data-contrast=\"none\">OK, let&#8217;s be practical. What was the first AI tool that you used? Was it ChatGPT, or something less well-known? What was your first reaction? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal<\/span><\/b><span data-contrast=\"none\">: The first breakthrough article that influenced me was <\/span><i><span data-contrast=\"none\">&#8220;Attention is All You Need&#8221;<\/span><\/i><span data-contrast=\"none\"> from Google. It introduced the first generation of Transformer models and the <\/span><i><span data-contrast=\"none\">self-attention mechanism,<\/span><\/i><span data-contrast=\"none\">which allows the model to analyze different parts of the input text with varying degrees of attention. This concept became the basis for other models, such as BERT and GPT, which began to specialize in different tasks &#8211; GPT for conversation, BERT for classification. <\/span><\/p>\n<p><span data-contrast=\"none\">My first real exposure to AI came in 2020 with GPT-3, which was a major turning point for me. This model demonstrated far more sophisticated manifestations of intelligence, which came as a big surprise to me. Around the same time, another important article also emerged: <\/span><i><span data-contrast=\"none\">&#8220;Scaling Laws for Neural Language Models&#8221;<\/span><\/i><span data-contrast=\"none\">, which discusses scaling laws. In it, the authors showed that increasing the size of the model, the amount of training data, and the computation time has a directly predictable effect on improving its performance. This principle is the basis for the development of advanced language models today. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> I started experimenting with different online platforms that could rephrase the text, expand it, or change its tone. But it was nothing groundbreaking \u2013 there was always a need to provide input text, and the tools often made up the information. So in practice, I used them only occasionally. <\/span><\/p>\n<p><span data-contrast=\"none\">The biggest problem was that when the AI added something, I had to check the result carefully, because it often generated incorrect or completely fabricated information. Either I didn\u2019t know how to prompt correctly, or the model itself was still imperfect. I couldn\u2019t get a consistently high-quality output. <\/span><\/p>\n<p><span data-contrast=\"none\">The turning point came in 2023, when OpenAI released GPT-4. That was the moment when artificial intelligence really took off and reached the form we know today. For ordinary users, this leap was huge. It was in that year that GPT-4 <\/span> <span data-contrast=\"none\">gained enormous popularity, with one million users signing up in the first week alone. This shows how massive the demand for this technology has been and how quickly it has been adopted by the public. <\/span><\/p>\n<div class=\"inside\"><div class=\"blog-quote\">\n    <div class=\"blog-quote--wrapper\">\n                <div class=\"blog-quote--content\">\n            <div class=\"top\">\n                <svg version=\"1.2\" class=\"topquote\" baseProfile=\"tiny\" id=\"Layer_1\"\n                     xmlns=\"http:\/\/www.w3.org\/2000\/svg\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\"\n                     x=\"0px\" y=\"0px\" width=\"200px\" height=\"141.111px\"\n                     viewBox=\"0 0 200 141.111\" xml:space=\"preserve\">\n                    <g>\n                        <g>\n                            <path d=\"M37.335,92.175c-4.4,11.067-11.333,22.001-20.601,32.535c-2.934,3.334-3.333,8.134-0.934,11.867\n                                c1.867,2.934,4.934,4.534,8.267,4.534c0.934,0,1.868-0.067,2.801-0.4c19.601-5.733,65.403-26.067,66.67-91.271\n                                C94.004,24.305,75.604,2.704,51.669,0.237c-13.268-1.334-26.468,3-36.269,11.8C5.6,20.905,0,33.572,0,46.773\n                                C0,68.773,15.601,88.042,37.335,92.175L37.335,92.175z\"\/>\n                            <path d=\"M158.075,0.237c-13.201-1.334-26.401,3-36.201,11.8c-9.803,8.868-15.401,21.535-15.401,34.736\n                                c0,22,15.602,41.269,37.335,45.402c-4.399,11.067-11.334,22.001-20.601,32.535c-2.934,3.334-3.335,8.134-0.935,11.867\n                                c1.867,2.934,4.936,4.534,8.268,4.534c0.933,0,1.867-0.067,2.8-0.4c19.602-5.733,65.404-26.067,66.67-91.271v-0.934\n                                C200.01,23.771,181.81,2.704,158.075,0.237L158.075,0.237z\"\/>\n                        <\/g>\n                    <\/g>\n                <\/svg>\n            <\/div>\n            <p class=\"quote-perex\"><span data-contrast=\"none\">The turning point in the use of AI came in 2020 with the release of GPT-3. AI has begun to become accessible to the general public. <\/span><\/p>                    <\/div>\n    <\/div>\n<\/div>\n<\/div>\n<p><b><span data-contrast=\"none\">How does artificial intelligence actually work? How does it understand our needs, anticipate them and react to make our lives easier? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal:<\/span><\/b><span data-contrast=\"none\"> When we talk about language models, their basis is the prediction of the next word \u2013 based on the previous text, they estimate what will follow. It\u2019s basically like a form of statistical regression. AI models are essentially large statistical models that learn from huge amounts of data from the internet. <\/span><\/p>\n<p><span data-contrast=\"none\">Interestingly, almost all the available data has already been used, so the focus of research today is on generating synthetic data to further improve the models. The new generation of models, like the aforementioned Transformers 2, brings a fundamental change &#8211; we will be able to extend those models during runtime (inference time). This means that models can learn, adapt and adjust their answers in real-time as we query them. This makes them even more accurate and efficient. <\/span><\/p>\n<p><b><span data-contrast=\"none\">What is your view, Jakub?<\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> I look at it more from the user perspective. Every day, I work primarily with OpenAI models \u2013 GPT, DALL\u00b7E <\/span><span data-contrast=\"none\">&#8211;<\/span><span data-contrast=\"none\">, and, most recently, Sora. I\u2019m not saying the other models are bad, but these are the ones I prefer. <\/span><\/p>\n<p><span data-contrast=\"none\">For me, it\u2019s not so important how they work, but what they can offer me. When I choose a tool, I evaluate it based on three main criteria: <\/span><\/p>\n<ul>\n<li data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"3\" data-list-defn-props=\"{\" aria-setsize=\"-1\" data-aria-posinset=\"1\" data-aria-level=\"1\"><span data-contrast=\"none\">Will it help me in my personal development? Will I gain insights from it, and will it help me broaden my horizons? <\/span><\/li>\n<\/ul>\n<ul>\n<li data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"3\" data-list-defn-props=\"{\" aria-setsize=\"-1\" data-aria-posinset=\"2\" data-aria-level=\"1\"><span data-contrast=\"none\">Will it save me time? Can it streamline my work or optimize tasks? Will it add value to my work or personal life in the long run? <\/span><\/li>\n<\/ul>\n<ul>\n<li data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"3\" data-list-defn-props=\"{\" aria-setsize=\"-1\" data-aria-posinset=\"3\" data-aria-level=\"1\"><span data-contrast=\"none\">Can it generate income? Can I use it for something that will justify the cost of using the tool? <\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"none\">With GPT, I realized after a few days that it was a tool that would help me grow quickly and save time<\/span><span data-contrast=\"auto\">.<\/span><\/p>\n<p><b><span data-contrast=\"none\">What has impressed you the most about ChatGPT? At what point did you decide that this was something you were going to use and that it was going to pay off? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> I first used it in high school. Back then, I didn\u2019t know how to craft effective prompts to get the desired output. There was a big surge around it \u2013 a million users in less than a week \u2013 so I was worried it might be discontinued. The system was crashing frequently due to overload. I tried to learn how to use it before it became inaccessible. But that didn\u2019t happen; it evolved over time, and today it\u2019s far more stable. <\/span><\/p>\n<p><span data-contrast=\"none\">Today, AI saves me hours of work and a lot of mental energy. It takes on tasks that would otherwise drain me \u2013 for example, brainstorming concepts. I recently needed to design a new model, and GPT helped me analyse the steps, determine the next course of action, and within nine hours, I had a working prototype. I didn\u2019t have to manually analyse all the details or write lengthy documentation \u2013 GPT retained context and could clearly explain its output, such as a piece of code it designed. <\/span><\/p>\n<div class=\"inside\"><div class=\"blog-quote\">\n    <div class=\"blog-quote--wrapper\">\n                <div class=\"blog-quote--content\">\n            <div class=\"top\">\n                <svg version=\"1.2\" class=\"topquote\" baseProfile=\"tiny\" id=\"Layer_1\"\n                     xmlns=\"http:\/\/www.w3.org\/2000\/svg\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\"\n                     x=\"0px\" y=\"0px\" width=\"200px\" height=\"141.111px\"\n                     viewBox=\"0 0 200 141.111\" xml:space=\"preserve\">\n                    <g>\n                        <g>\n                            <path d=\"M37.335,92.175c-4.4,11.067-11.333,22.001-20.601,32.535c-2.934,3.334-3.333,8.134-0.934,11.867\n                                c1.867,2.934,4.934,4.534,8.267,4.534c0.934,0,1.868-0.067,2.801-0.4c19.601-5.733,65.403-26.067,66.67-91.271\n                                C94.004,24.305,75.604,2.704,51.669,0.237c-13.268-1.334-26.468,3-36.269,11.8C5.6,20.905,0,33.572,0,46.773\n                                C0,68.773,15.601,88.042,37.335,92.175L37.335,92.175z\"\/>\n                            <path d=\"M158.075,0.237c-13.201-1.334-26.401,3-36.201,11.8c-9.803,8.868-15.401,21.535-15.401,34.736\n                                c0,22,15.602,41.269,37.335,45.402c-4.399,11.067-11.334,22.001-20.601,32.535c-2.934,3.334-3.335,8.134-0.935,11.867\n                                c1.867,2.934,4.936,4.534,8.268,4.534c0.933,0,1.867-0.067,2.8-0.4c19.602-5.733,65.404-26.067,66.67-91.271v-0.934\n                                C200.01,23.771,181.81,2.704,158.075,0.237L158.075,0.237z\"\/>\n                        <\/g>\n                    <\/g>\n                <\/svg>\n            <\/div>\n            <p class=\"quote-perex\"><span data-contrast=\"none\">&#8216;AI saves me several hours and a lot of mental energy every day. It takes on tasks that would otherwise be exhausting for me. I can now devote that time to more important things.&#8221;  <\/span><span data-ccp-props=\"{\"134245417\":false,\"335559738\":240,\"335559739\":240}\"> <\/span><\/p>                    <\/div>\n    <\/div>\n<\/div>\n<\/div>\n<p><span data-contrast=\"none\">In addition to creative support, AI also helps me with decision-making. When I have multiple options, I outline key points, and it helps me evaluate which is the most logical choice. Sometimes it\u2019s useful to have an independent perspective, and AI can provide that. <\/span><\/p>\n<figure id=\"attachment_20913\" aria-describedby=\"caption-attachment-20913\" style=\"width: 1200px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-20912 size-full\" src=\"https:\/\/performance-msg-life-sk.rucolabs.sk\/wp-content\/uploads\/2025\/03\/Jakub-Michal-IT-odbornici-msg-life-1200x800-1.webp\" alt=\"Jakub and Michal use AI mainly at work.\" width=\"1200\" height=\"800\" srcset=\"https:\/\/performance-msg-life-sk.rucolabs.sk\/wp-content\/uploads\/2025\/03\/Jakub-Michal-IT-odbornici-msg-life-1200x800-1.webp 1200w, https:\/\/performance-msg-life-sk.rucolabs.sk\/wp-content\/uploads\/2025\/03\/Jakub-Michal-IT-odbornici-msg-life-1200x800-1-300x200.webp 300w, https:\/\/performance-msg-life-sk.rucolabs.sk\/wp-content\/uploads\/2025\/03\/Jakub-Michal-IT-odbornici-msg-life-1200x800-1-1024x683.webp 1024w, https:\/\/performance-msg-life-sk.rucolabs.sk\/wp-content\/uploads\/2025\/03\/Jakub-Michal-IT-odbornici-msg-life-1200x800-1-768x512.webp 768w, https:\/\/performance-msg-life-sk.rucolabs.sk\/wp-content\/uploads\/2025\/03\/Jakub-Michal-IT-odbornici-msg-life-1200x800-1-390x260.webp 390w\" sizes=\"auto, (max-width: 1200px) 100vw, 1200px\" \/><figcaption id=\"caption-attachment-20913\" class=\"wp-caption-text\">Jakub and Michal use AI mainly at work.<\/figcaption><\/figure>\n<p><b><span data-contrast=\"none\">Since the topic is AI in practice, could you give a few more examples of how it can be used effectively, and how often you use it?<\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal:<\/span><\/b><span data-contrast=\"none\"> First and foremost, I use AI at work &#8211; in programming and training models. Large language models help us find information and optimize processes. <\/span><\/p>\n<p><span data-contrast=\"none\">In addition, I also use AI in investing, trading and news tracking. I work with time series models that can predict trends, and I build some of the models myself. They are much more sophisticated than conventional statistical indicators such as moving averages. I also use visual analysis models that can process images and analyse charts, identify levels or trends and then use them in various applications. <\/span><\/p>\n<p><span data-contrast=\"none\">However, AI also helps me with my everyday learning and improves my understanding of the world. Nowadays, it&#8217;s relatively easy to understand complex research texts \u2014 simply enter them into ChatGPT and it will explain them to you in plain language. Anyone can try it out. It&#8217;s a huge help, particularly if you&#8217;re unfamiliar with the technical formulas or terminology. I recommend that everyone tries it with a topic they don&#8217;t understand to see how the AI can explain it. <\/span><\/p>\n<p><span data-contrast=\"none\">And now for something a little more light-hearted \u2013 I also use AI for unconventional purposes. For instance, at the weekend I enjoy making creative breakfasts and arranging different images out of eggs and vegetables on my plate. What&#8217;s the ultimate level of this fun? I let the AI analyse my &#8216;artistic creation&#8217; and tell me what it sees. It&#8217;s fascinating how it recognises different patterns \u2014 for instance, where I see a volcano with a lava-like egg yolk, the AI interprets the surrounding vegetables as flowers. I often think back on it and see something new in the image. It&#8217;s such an unexpected and creative experiment! <\/span><\/p>\n<p><b><span data-contrast=\"none\">Jakub, what else would you add from practice?<\/span><\/b><\/p>\n<p><span data-contrast=\"none\">Since I&#8217;ve been able to use GPT to search the internet and find the resources I need, I&#8217;ve been using Google a lot less. Now, when I need something, I ask GPT first and then head to the search engine. The AI quickly summarises the information and provides the source directly, saving me time. <\/span><\/p>\n<p><span data-contrast=\"none\">What\u2019s important to me is where the information comes from, not just what the AI tells me. I don\u2019t care what it tells me, I care where it got it from. That\u2019s why I always ask for the source. This means I don\u2019t even have to formulate prompts. Just give me a brief description of the problem, and GPT will help me find the answer faster than if I try to formulate the question correctly in Google. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Could you suggest some practical uses of ChatGPT for complete beginners and advanced users alike?<\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal:<\/span><\/b><span data-contrast=\"none\"> ChatGPT is certainly an exciting tool. It allows you to process text, analyse images, think and make decisions. It makes my job a lot easier, especially in three areas. <\/span><\/p>\n<p><span data-contrast=\"none\">For those who develop systems like me \u2013 models help us eliminate noise from user input. It used to be that the user had to articulate exactly what they wanted, but today it doesn\u2019t have to be so precise. A model understands the approximate input and can extract the essentials from it. For example, when I\u2019m programming, I don\u2019t have to write full sentences, I just need a two- or three-word description, a few keywords, and the model already knows what I need. <\/span><\/p>\n<p><span data-contrast=\"none\">The second area is logic and the ability to think. Sometimes, I pit multiple AI models against each other. One takes my input and generates an output \u2014 that is, it does what I want it to do. The other critiques what the first one produced. The third acts as a consensus moderator. I let them work this way for half an hour to get different perspectives on the problem. This often leads to solutions that I wouldn&#8217;t have come up with on my own. <\/span><\/p>\n<p><span data-contrast=\"none\">The third area is handling complex topics and communicating in real time. ChatGPT helps me to understand even brand new or highly complex topics without me needing to be an expert on them. I simply ask it a question and it explains the topic to me in simple terms. I also use Advanced Voice Mode a lot, as it enables the AI to respond naturally. I can interrupt it and rephrase the question if I want a different answer. For me, ChatGPT is literally a digital wingman that I discuss various topics with on my way home. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Jakub, what is your view on ChatGPT?<\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> I use it every day \u2013 it&#8217;s an essential tool for me. However, I often notice how people around me who don\u2019t have much experience with AI perceive it. They often think of it as a soothsayer that will instantly provide them with the exact answer they need. It just doesn\u2019t work that way. <\/span><\/p>\n<p><span data-contrast=\"none\">As Michal mentioned, you can type just two or three words and the model will understand, but only if it already has some context. I also use it by providing a brief summary, which ChatGPT then understands. However, if I start a completely new conversation, the results can be way off because the model has no prior information. <\/span><\/p>\n<p><span data-contrast=\"none\">Let&#8217;s use an example. Imagine I want to eat. I&#8217;ll come to your place and say, &#8220;Make me my favorite food.&#8221; How would you respond? You have no idea what my favorite food is. So you&#8217;d probably try to improvise, because you have to do something. You have to come back with an answer. You&#8217;d probably try to make something that you think I might want. But would it really be what I want? Probably not. And ChatGPT works the same way &#8211; if you don&#8217;t give it context, it has to make assumptions.<\/span><\/p>\n<p><span data-contrast=\"none\">But if I came to my mother or grandmother with the same question and they had that context, they would know right away what I like. They wouldn&#8217;t have to guess. The same goes for artificial intelligence &#8211; if it has context, it works more accurately. You don&#8217;t have to be afraid to guide the AI a little bit more, to interact with it. You can give it more detail in the beginning. Ask it what input it needs from you to give you the output you want. <\/span><\/p>\n<p><span data-contrast=\"none\">People perceive ChatGPT as a fortune teller who instantly answers everything they need. But AI works more accurately when it has context. <\/span><\/p>\n<p><b><span data-contrast=\"none\">However, one thing is certain. Artificial intelligence will never be able to cook as well as your grandma.<\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> It certainly won&#8217;t. But, for example, two weeks ago I wanted to make dinner and I only had a few ingredients. I put them in ChatGPT and asked what I could cook with them. The result was surprisingly tasty. So even when it doesn&#8217;t cook, it can come up with interesting recipes. <\/span><\/p>\n<p><b><span data-contrast=\"none\">How can you ask ChatGPT questions correctly? I recently asked Michal a simple question: &#8216;When were you born?&#8217; He answered: &#8216;In May.&#8217; I was surprised because I wanted to know the year, but I had worded the question incorrectly. Does it work similarly with ChatGPT? If we phrase the question incorrectly, will we receive an inaccurate answer?<\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal:<\/span><\/b><span data-contrast=\"none\"> Exactly. If the question is vague or too broad, the answer will be similarly vague or broad. The general rule is that the more specific the question, the more precise the answer. <\/span><\/p>\n<p><span data-contrast=\"none\">Humans make a number of mistakes when working with AI. One such mistake is combining too many questions into one. This can cause the model to become confused and not provide the exact answer we want. Therefore, it is a good idea to ask questions clearly and unambiguously. <\/span><\/p>\n<p><span data-contrast=\"none\">Another common mistake is that people blindly trust everything AI generates. While ChatGPT is very advanced, it can still produce inaccurate or distorted information. That\u2019s why it\u2019s important to check the facts, for example by searching on Google. Just type in keywords and verify your sources. <\/span><\/p>\n<p><span data-contrast=\"none\">Many also assume that artificial intelligence knows everything, but this is not true. Its knowledge is limited and it does not have up-to-date access to all information. Another mistake is using overly complicated language &#8211; if a question is unnecessarily complex, the model may answer less accurately. It is best to phrase questions simply and directly. <\/span><\/p>\n<p><b><span data-contrast=\"none\">So, how do you get started with artificial intelligence, and what costs are involved? Are there any interesting tools that you would recommend to listeners? What can they be used for? And more specifically, how do you choose the right AI tool, and how much should you expect to spend on AI software subscriptions each month? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> At the moment, I\u2019m a regular user; I don\u2019t use the API (web browser) for AI, although I have an account. I only pay for ChatGPT Plus at the moment, but I can pay extra if I need more. On average, it costs tens of euros a month, so it&#8217;s not a significant expense. If you&#8217;re just starting out, I&#8217;d definitely recommend beginning with GPT \u2013 the basic version is free and provides a good introduction to the technology. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Michal:<\/span><\/b><span data-contrast=\"none\"> I agree. ChatGPT by OpenAI is the best start &#8211; it&#8217;s free, although it has limits. If one runs into limitations, one can pay $20 a month for advanced features. <\/span><\/p>\n<p><span data-contrast=\"none\">However, I also use AI through the API &#8211; I&#8217;m writing a program that connects to ChatGPT. As I mentioned earlier, I&#8217;m building multiple models against each other to critically evaluate the outputs. If you want to access the latest OpenAI models via the API, you first have to spend $1,000 to get Tier 5 (long-term user) status &#8211; a level that allows you to use the latest versions of the models. <\/span><\/p>\n<p><span data-contrast=\"none\">Interestingly, on January 20, the Chinese company DeepSeek released a new open model, achieving O1 results, which is currently one of the best models. Open means you can install it directly on your computer and don\u2019t have to send data to external servers. <\/span><\/p>\n<p><span data-contrast=\"none\">If it&#8217;s about using AI over APIs and even weaker models are enough, the prices are actually very low &#8211; you pay for tokens (the words that the model processes). It costs me about $5 a month, which is less than a ChatGPT Plus subscription. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> Then again, if convenience is the priority, paying $20 a month for hassle-free access on the app is still the better option. If the price went up to $100, however, I&#8217;d be considering my own solution. At the current price though, I think it&#8217;s worth it for the convenience. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Michal, you mentioned advanced features. Are they worth using? And what exactly do you use them for? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal<\/span><\/b><span data-contrast=\"none\">: One of these is Advanced Voice Mode, which I&#8217;ve already mentioned. This feature allows me to talk to the AI in real time. Originally, it was only available in the paid version, but it has since been made available to a wider audience. However, there is still a limitation. If you want to brainstorm or have a natural conversation with the AI, it&#8217;s definitely worth checking out. <\/span><\/p>\n<p><span data-contrast=\"none\">Another advanced benefit of the Plus version is access to the latest models. As soon as OpenAI releases a new model, subscribers get it first, while users of the free version wait longer. So if you want to always have the latest and greatest performance, it&#8217;s worth investing in the paid version. <\/span><\/p>\n<p><b><span data-contrast=\"none\">If someone is considering using tools like ChatGPT, what should they know in order to get the most out of it? Are all versions paid? What should the user rather avoid? And how is the paid version better? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub<\/span><\/b><span data-contrast=\"none\">: ChatGPT is also free to use. It was even possible to try it without registration for a while, I don&#8217;t know if that is still valid. Basically, you just have to open the site, register in a moment, or use your Google account to log in. <\/span><\/p>\n<p><span data-contrast=\"none\">GPT-4o is currently available on a limited basis. OpenAI does not disclose how many messages or tokens users of the free version can send. However, if you exceed your limit, the system will either switch you to GPT-3.5 or prompt you to try again later, when you will be able to use the full version again. If you need to write more, you can pay extra. If not, you won&#8217;t be charged. I like OpenAI&#8217;s philosophy that they&#8217;ll give everyone access when they develop something new. First to paying users, of course, but a limited version is released a few months later. <\/span><\/p>\n<p><span data-contrast=\"none\">$20 a month for the Plus version is not a large sum. In my opinion, it&#8217;s a worthwhile investment because the technology is constantly evolving. What many people don&#8217;t realise is that OpenAI has received substantial backing from Microsoft, which has invested around $13 billion in the company in recent years. Because of this, many people don&#8217;t realise that OpenAI has significant development resources. In turn, Microsoft integrates these models into Bing, Copilot, and Bing Chat for search. It&#8217;s running GPT-4 Turbo there, which is not available directly through the ChatGPT site. Running Bing Chat gives you access to a more powerful version of the model than is normally available in the free version of ChatGPT. <\/span><\/p>\n<p><span data-contrast=\"none\">As for the versions, all advanced AI models are paid for nowadays. I remember when OpenAI first released DALL-E for image generation. Initially, it was free, offering a limited number of tokens per month. You could generate 10 to 15 images; each token meant four images. It could generate quite abstract images based on text. Things that basically didn&#8217;t exist. For example, you could generate an image of a cat on a skateboard or a cat as an astronaut in space. <\/span><\/p>\n<p><span data-contrast=\"none\">The O1 and O3 models that are emerging now have advanced logical thinking and planning capabilities. Another interesting development is the multimodal AI Sora, which combines text, images and videos. I\u2019m testing its video generation capabilities, but I\u2019m not yet fully satisfied with the results. <\/span><\/p>\n<p><span data-contrast=\"none\">Everyone has to choose a model according to their needs. If I were starting from scratch with AI, ChatGPT would definitely be my first choice. Just sign up and give it a try! If the free version meets your needs, that&#8217;s great. Otherwise, you can always pay extra to access the advanced features. <\/span><\/p>\n<p><b><span data-contrast=\"none\">What are the actual differences between the latest version and the previous one? Are they that different? We discussed the various models: ChatGPT is free, DALL-E is geared towards marketing and graphic design, and o1 is intended for science and mathematics, offering more advanced analytical capabilities. Is ChatGPT sufficient for the average user? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> Yes, that&#8217;s right \u2014 you can either use the free version or pay for a subscription. Personally, I don&#8217;t use DALL-E or Sora that often. I know Sora has some limitations within the subscription. For example, even as a paying user, you can&#8217;t generate videos of the highest quality \u2014 I had a limit of four seconds per video, as well as limits on the number of characters in the description and the total number of videos I could generate. This makes sense, as generating videos is much more computationally intensive than typing with ChatGPT. <\/span><\/p>\n<p><span data-contrast=\"none\">When it comes to the differences, it&#8217;s all about the speed of the responses and the available features. If you exceed the GPT-4o limit, you will automatically be switched to o4-mini. This model is slightly slower and may have poorer response quality and limited features. <\/span><\/p>\n<p><b><span data-contrast=\"none\">How exactly are those algorithms set up? Last time, I wondered when it would switch me from the higher version to the mini version. How does that work? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> This is exactly what Michal mentioned \u2014 it&#8217;s about tokens. The model counts how many tokens you consume, i.e. how many input and output words have been processed. When you reach your limit, it simply switches you to a weaker version. It&#8217;s not random; it&#8217;s not an algorithm that just &#8216;turns you off&#8217;. It simply informs you that you have used up the permitted number of tokens and that you can return in a few hours. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Michal:<\/span><\/b><span data-contrast=\"none\"> I would add to the o1 model &#8211; it is not just for research and math analysis. It has a function called <\/span><i><span data-contrast=\"none\">chain of thought<\/span><\/i><span data-contrast=\"none\">, which means that it thinks for some time before answering. The outputs are then more logical and of higher quality. For simple questions, it answers quickly, but if it is given a more complex task, it may think about it for a minute. So, in my opinion, it is also usable for ordinary users, not only for scientists and analysts. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> That\u2019s a good point \u2013 I had completely forgotten about this! The interesting thing about the O1 is that when you give it a command, it doesn\u2019t just show how long it has been thinking for. If you click on it, however, you can see the whole <\/span><i><span data-contrast=\"none\">chain of thought<\/span><\/i><span data-contrast=\"none\">, i.e. the sequence of its thoughts.<\/span><\/p>\n<p><span data-contrast=\"none\">You see step by step how the model proceeded &#8211; what it considered, what options it evaluated, what variables it took into account, and why it ultimately came to a particular conclusion. So it&#8217;s not just a random answer generated or an artificially delayed response time. You can really see that it went through some logical process before it gave you a final answer. <\/span><\/p>\n<p><b><span data-contrast=\"none\">How can IT professionals effectively use AI tools in companies to comply with security policies? What should they be most careful about? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> The basic rule for me is simple: no sensitive data, whether corporate or private. I think of AI as a database in which I store information, but I never send anything confidential. I always consider what I&#8217;m sending to the AI, whether it&#8217;s corporate or private data. <\/span><\/p>\n<p><span data-contrast=\"none\">For example, when I solve a technical problem for a colleague, I never enter any sensitive data, such as a specific machine number. Instead, I describe the problem in general terms. &#8220;I have a problem like this: I found this solution, but I need some advice.&#8217; This way, I can receive a response without compromising security.<\/span><\/p>\n<p><span data-contrast=\"none\">The same applies online. Don&#8217;t post pictures on Facebook that you wouldn&#8217;t want someone to use against you 10 years from now. The same goes for AI \u2014 you need to think twice about what you post. Everyone should set their own boundaries, but it&#8217;s definitely a good idea to use AI sensibly and consider security. <\/span><\/p>\n<p><span data-contrast=\"none\">Do not use the AI tool for any sensitive work or privacy data.<\/span><\/p>\n<p><b><span data-contrast=\"none\">Michal<\/span><\/b><span data-contrast=\"none\">: I would expand on this a little further: it&#8217;s not just personal or company data, but also information that could reveal how a company works, including its systems, architecture and strategic plans. Providing details to AI about how we plan something could backfire on us. <\/span><\/p>\n<p><span data-contrast=\"none\">It is important to share as little specific information as possible. If we need to consult with AI about a problem, it is better to formulate it in general terms, without direct connection to our company or project. <\/span><\/p>\n<p><span data-contrast=\"none\">If you don&#8217;t trust the models at all and don&#8217;t want your data to leave your computer, you can run them locally. However, running AI models quickly requires a powerful graphics card \u2014 ideally two with at least 45\u201355 GB of NVRAM. <\/span><\/p>\n<div class=\"inside\">\n<div class=\"tip center\">\n    <div class=\"tip-wrap\">\n                     <img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/performance-msg-life-sk.rucolabs.sk\/wp-content\/themes\/msg\/assets\/img\/recommend.svg\" alt=\"Recommend\" width=\"60\" height=\"60\">\n                 <div class=\"tip-wrap-content\">\n            <div class=\"tip-wrap-title\">\n                We recommend:            <\/div>\n            <\/p>\n<p><span data-contrast=\"none\">Listen to our <\/span><a href=\"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/podcasts\/podcast-work-ai\/\" target=\"_blank\" rel=\"noopener\"><span data-contrast=\"none\">Podcast #2: AI and the future of IT work<\/span><\/a><span data-contrast=\"none\"> and learn how AI will impact the work of IT professionals in the future.<\/span><span data-ccp-props=\"{}\"> <\/span><\/p>\n<p>\n        <\/div>\n    <\/div>\n<\/div>\n<\/p><\/div>\n<p><span data-contrast=\"none\">Some of the open models you can install include Llama 3 or some vision models capable of analyzing images. Today, such a setup with the necessary power can be bought for around \u20ac1,000. If you are looking for a bargain, the NVIDIA RTX 3090 second-hand can be acquired for around \u20ac500. It still has the best price\/performance ratio. <\/span><\/p>\n<p><span data-contrast=\"none\">The AI model can be run without a graphics card, but then everything is done in RAM and on the CPU, which is extremely slow. There is also the possibility of a combination \u2013 part of the model can run in RAM and part on the GPU, but it\u2019s still not ideal. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Jakub:<\/span><\/b><span data-contrast=\"none\"> The difference lies in the number of processors. GPUs have many more compute cores than regular CPUs. This is why graphics cards are essential for AI \u2014 they can handle parallel computations much faster. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Michal: <\/span><\/b><span data-contrast=\"none\">Small<\/span> <span data-contrast=\"none\">models up to 10 GB of VRAM can be used, but their capabilities are quite limited. They work for simple tasks, but you can&#8217;t do much with them. <\/span><\/p>\n<div class=\"inside\">\n<div class=\"tip center\">\n    <div class=\"tip-wrap\">\n                     <img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/performance-msg-life-sk.rucolabs.sk\/wp-content\/themes\/msg\/assets\/img\/recommend.svg\" alt=\"Recommend\" width=\"60\" height=\"60\">\n                 <div class=\"tip-wrap-content\">\n            <div class=\"tip-wrap-title\">\n                We recommend:            <\/div>\n            <\/p>\n<p><span data-contrast=\"none\">Read also our<\/span> <a href=\"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/articles\/digitization\/internet-safety-tips\/\"><span data-contrast=\"none\">internet safety tips<\/span><\/a><a href=\"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/articles\/digitization\/internet-safety-tips\/\" target=\"_blank\" rel=\"noopener\"><span data-contrast=\"none\"> to help you stay safe online<\/span><\/a><span data-contrast=\"none\">.<\/span><span> <\/span><\/p>\n<p>\n        <\/div>\n    <\/div>\n<\/div>\n<\/p><\/div>\n<p><b><span data-contrast=\"none\">Have you ever used AI for something unusual? For example, in what ways has this tool pleasantly surprised you or even unpleasantly disappointed you? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Michal<\/span><\/b><span data-contrast=\"none\">: I also use Chinese models, and it is fascinating how they work in image analysis. The model first extracts features from the image and then processes them. I recently came across an interesting situation \u2013 I was analyzing an English text. Since it was a Chinese model, it misinterpreted it as Chinese characters. This is an example of how training data affects AI performance. I often encounter surprises like this when developing these systems \u2013 they are not always pleasant. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Thank you, Michal and Jakub, for introducing us to the world of artificial intelligence today. If you could give the audience one piece of advice, what would it be? <\/span><\/b><\/p>\n<p><b><span data-contrast=\"none\">Jakub<\/span><\/b><span data-contrast=\"none\">: Don&#8217;t be afraid of AI! Many people are worried that AI will take their jobs. But let&#8217;s look at history: people used to plough with horses and ploughs; then tractors came along. The work didn&#8217;t disappear; just the tools changed. Rather than fearing AI, it&#8217;s better to learn how to use it to your advantage and add value. AI isn&#8217;t dangerous; it just needs to be understood and used wisely. <\/span><\/p>\n<p><span data-contrast=\"none\">AI won&#8217;t take our jobs. Only the tools we use to do our jobs change with it. <\/span><\/p>\n<p><b><span data-contrast=\"none\">Michal<\/span><\/b><span data-contrast=\"none\">: AI agents are the future. This trend allows AI agents to communicate with each other and solve tasks together. We can model the dynamics of their collaboration, and I think this is the future \u2013 creating entire teams of machines to work on our behalf. <\/span><\/p>\n<p><span data-contrast=\"none\">Dear listeners, today\u2019s podcast was a real journey of discovery for me. I hope you found it interesting, and that we added a dash of humour while providing you with new insights. AI has the power to fascinate, surprise and amuse us. What is the message at the end? Don&#8217;t be afraid to try new technologies! The more you learn about them, the easier it will be to use them to your advantage. I look forward to seeing you on the next episode of <\/span><a href=\"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/podcasts\/\" target=\"_blank\" rel=\"noopener\"><span data-contrast=\"none\">Na vlne kodu<\/span><\/a><span data-contrast=\"auto\">.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Get valuable tips on how AI can be used effectively in practice and find out how you can make it your ally.<\/p>\n","protected":false},"author":35,"featured_media":20916,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[157],"tags":[252,270],"class_list":["post-23226","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-podcasts","tag-ai-artificial-intelligence-en","tag-interviews-en"],"acf":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/posts\/23226","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/users\/35"}],"replies":[{"embeddable":true,"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/comments?post=23226"}],"version-history":[{"count":3,"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/posts\/23226\/revisions"}],"predecessor-version":[{"id":24592,"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/posts\/23226\/revisions\/24592"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/media\/20916"}],"wp:attachment":[{"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/media?parent=23226"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/categories?post=23226"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/performance-msg-life-sk.rucolabs.sk\/en\/wp-json\/wp\/v2\/tags?post=23226"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}