0:00 If they understood the problem, they wouldn't be hiring you, they'd have fixed it themselves. Simple is complicated enough, especially at scale. There's a lot of people trying to adopt new technology just for the sake of it, and that is something that a good engineer doesn't do. 0:12 The good architects are usually the ones where magically everything goes well and nobody knows exactly why. 0:17 What is your advice for people that really want to become great software engineers? What do they need to do? 0:25 What is your advice for people that really want to become great software engineers? What do they need to do? 0:31 Increase your breadth. There's a lot of focus on the depth early on in your career, which is important, and there's an advice that perpetuates which says focus, true focus. 0:44 But at the same time don't dismiss everything else that's happening. Increase your breadth. 0:49 Personally, I optimised one thing that really got me far, which is having the ability to learn effectively in very short periods of time. And that's why whenever I tackle a problem, I don't have a problem digging really deep into 1:04 anything UI encounter from quantum mechanics all the way to any technical problem that I face on a day-to-day basis. 1:14 I'm a, you know, I'm a university dropout. 1:17 I never finished my computer science education, but that did not deter me from picking up that education myself and really digging deep into all sorts of theoretical topics, but also practical areas and topics. And I'm a perpetual learner. 1:31 So in my opinion, the next phase where we're heading, it's going to require people to be able to learn really fast, get out of their comfort zone really fast, dig deep really fast, and attain high levels of functional proficiency in any new area. 1:47 And then attaining mastery is not always required in everything. So just pick a few topics where you attain mastery in but also increase your breadth. 1:56 And if we are talking about the skills that are for the future, you're saying technology accelerates quite quickly. 2:01 What are some of the skills that you think people should focus on specifically for their career but also for like peace of fulfilment and looking towards the future? 2:08 The ability to learn first and foremost. 2:11 None of the tools I work with I I learned I learned SPSS people back in the day, some some people in the audience will be cringing right now. SPSS taught myself R to scrape Twitter back before it became shitter to to model the 2013 2:30 fourteen Syrian refugee crisis. I hated Putin before I knew where Ukraine was on the map, but from our I went into Python And now Python is the end all be all. 2:42 But I'm from an era where people were still asking like Are you sure? Should you be learning SAS? 2:48 Because SAS is better in the market right now. 2:51 So God knows what we'll be using in 10 in 10 years. 2:54 Unless all the all the LLM start over fitting on on just languages that are already in use. 3:01 We might actually see a stagnation in the development, in the development of coding languages now, since Claude and Gemini will not be able to adopt to new languages as much as produce more Java horrors, meaning we will be stuck with 3:15 Java until the he death of the universe, I'm pretty sure. 3:20 But what I'm trying to show here is that those tools, those techniques, cloud platforms, they change so fast that you can't focus on learning a technique. 3:29 You got to learn a method to learn new stuff. 3:32 That is the most single and most important skill in the entire tech field to be able to learn, not even master, but just work with new tech. Anytime I have a new project, oh God, it's a new cloud platform I haven't worked with. 3:47 OK, well AWS, Google, Azure, I'm pretty sure it has most of the same functionalities. They they just call every damn button differently and that's how they vendor lock. 3:57 So, so you can't go go to the other cloud platform because the names is different, which is less of a hurdle than you would think. And then there's of course nuance, like the billing models are different, the scaling is different. The, the, the type of servers 4:12 you can run it in is different. You cannot local host, I mean sovereign this this version. Remember that people sovereignty is the new local host. You're just running your own damn model on your own damn computer. 4:28 But you don't call it local host you you call it sovereign. 4:31 The client will love it, thank me later. 4:34 So it's the and that's the other thing. 4:38 And I mentioned that before understanding the words because buzzwords will come, but they usually mean something that wasn't new at all. Again, sovereignty is just local host but new. Everybody screams as as was screaming AI, but we mainly meant just deep learning on 4:56 steroids with a lot a lot of GPU and compute. 4:59 Big data was just data that you store on multiple different servers because you don't have a single server that can contain it all. But nowadays my laptop has more storage than a whole complex of servers a decade ago. 5:11 Big data is dead. Long live big data. 5:15 The core problem here is the core problem of humanity, which is that sometimes we say the same words but we mean different things, and sometimes we say different words but we mean the same thing. And all of miscommunication stems from this. And in our field, it is 5:32 important to figure out not just what words people are using, which is what sales heavily focuses on, but what their actual problem is and what they actually mean, which can be, which can be completely different from the words they're actually using. Because I've had clients that 5:48 that ask for AI and it can mean a random tree, a random forest, It can mean you have some kind of image recognition model. 5:56 It can mean some type of speech synthesis. 5:59 It can mean producing synthetic data of bananas using 3D models. 6:05 It can mean so many different things, but they all use the same word and it's our job to figure out what the heck they want and then to build that. Not just to receive orders and build something, because that job will be outsourced and 6:18 automated to hell him back by whatever cloud copilot thing they they buy and or consume. But the core skill to figure out what the fluff they actually want and need and what is the problem behind the problem. Because if they understood the 6:36 problem, they wouldn't be hiring you, they'd have fixed it themselves. But they do not understand the problem, do not understand the solution. 6:42 It's our job to figure out that solution, then do that. 6:45 And to do that we need to be able to learn new tech and learn new stuff. And that's why learning is key. 6:53 What have you seen in how architects execute that makes them really good architects for the people that actually go on that career path? Yeah, I always say, I mean, first comment would be it's not a sort of binary choice or I don't think that being an architect is determined by 7:07 what's on your business card. So I think you can be a technical product person with a very architecture mindset, right for me. Well, let me start the other way around. The the bad architects are easier to spot. The good architects are usually 7:22 the ones where magically everything goes well and nobody knows exactly why the bad architects are easier to spot. 7:28 And it's like people who spew out a lot of buzzwords, you know, it's like, oh, everything must be cloud native or loosely coupled. Now I don't need an architect to tell me that. I can just put a poster on the wall. And then why? 7:40 Why do I need this? This person or people who believe they should have all the decision power. 7:46 It's like, oh developers, I'm here to guide you. 7:48 You should make 3 components, right? 7:50 No more, no less. And those I find the not so stellar architects, the mantra that we have in the workshop and that I, that I very much follow is that architects shouldn't try to be the smartest people, but they should make everybody else smarter. All right, that's an amplifier. 8:09 You don't want to be a kind of Oracle. 8:11 When people come with the questions and look for magic answers, Oh, what should we do? People come to me, right? 8:16 And I'm like, well, it's kind of charming, but how, how do I know it's your project? It's your application, right? 8:21 How can I make all the decisions for you? 8:24 But what I can do is help you make a, a better decision. 8:28 And I think to me, that is one of the characteristics of a, of a great architect. You can absorb the context, things that people explain to you, but you can uncover blind spots or maybe help people see different points of view, 8:41 different angles, distilled trade-offs that they might be implicitly making, but they're not aware of those kind of examples. I think that makes a great architect and it makes a nice architect if you wish, because you're not trying to be the the ivory tower big boss, but he 8:58 actually an amplifier to the team. 9:01 Any other foundations or fundamentals you want to highlight that distinguishes great engineers from not so great ones? If I look at what is happening in, in, in picnic context again, what what really strikes me is that our our engineering culture is relatively uniform in the 9:25 sense that we started only 10 years ago. 9:27 We have a very strong developer platform that was developed from the get go. And there, what I see in some other companies and other contexts is that there's a lot of people trying to adopt new technology just for the sake of it. And that is something that I 9:49 feel that a good engineer doesn't do right. 9:51 So if you adopt new technology, if you find out about a new technology, you need to understand whether it's actually an improvement of what you have. Make very clear also why that is the case and not just jump on any, any bandwagon. 10:08 And that's something that I feel that very good engineers are good at, right? So they there's this sites, I'm not sure if you know it, the boring technology dot COP. 10:17 I don't know it, but that sounds really funny. 10:19 Yeah, yeah. Which sort of advocates for use what works, use what is proven use and then use it in a very effective way. As you mentioned that that is I think what what good engineers do and discerning between OK, but what new technology is that interesting to jump onto 10:37 etcetera. And that is super hard, of course, and also maybe a bit more of an art than than a science sometimes. But it's precisely that's kind of gut feeling, I would say that's that that knowledge, that wisdom that you have as a, as a, as a Craftsman, as an engineer, 10:55 that sets you apart from people who, yeah, who don't have that taste or who don't have that knowledge to, to make a good decision. And then sometimes you end up in situations where there's companies that are much smaller than than the company I work at that have like dozens of 11:12 different technology stacks because, well, people decided that in some kind of context, it was better to use Rust or to use Go or to. And then you end up with this fantastic collection of technologies that nobody really knows how to manage anymore, really know how to, how to 11:29 operate anymore, really knows how to, how to bring this together. And yeah, that's, I think one of the hallmarks to come back to your question of a good engineer is to actually also limit this and, and, and, and stick to, yeah, proven things and what works. 11:45 Yeah. Is this then your advice as well? So to stick with what you have, start with the initial design that is simple and then stick with it until you actually reach certain limits and you can kind of based on your usage, forecast what the next. 11:59 Iteration would precisely if I was a start up founder or acto of a start up right? I would never go and start building for 100 X scale. Even if I'm like a firm believer in my idea and know that it's going to reach the masses and 12:12 it's going to be global. I would never design for that. 12:15 I would design for getting 100 users or maybe even 1000, right? 12:20 And I would just run everything on a single VM, to be honest. 12:22 Maybe 2, make it a bit more available. 12:25 I would not go and build massive database clusters. 12:29 Just start with one, maybe 2 nodes tops. 12:32 Replication, that's it. And this will like carry you really, really far. To be honest, once I attain or I'm get, I'm like close to 80% of these limits of what my resources can do. And by the way, vertical scaling can take you a long way. Like you have no idea. 12:50 We have my SQL nodes that have hundreds of CP us on them. 12:57 So you don't really need to go and start sharding and doing all sorts of fancy stuff when vertical scaling can still carry you. And right now with cloud native solutions, you can go pretty far. 13:09 Like you can get a one VM with 120 CP cores, right? 13:13 You can get terabytes of memory, Yeah. 13:17 And that can do a lot for you. You don't need to start doing horizontal scaling before you get you really start hitting these limits. That's what I've seen where it's challenging for people, where they say OK, I'm a little bit of a perfectionist. I value quality in what I do on 13:30 a day-to-day. My job is basically part of who I am. And if I don't deliver the highest quality that I can in this aspect, like I'm doing myself with this justice. And it's very like, if I lay it out like that, it might sound selfish, but those people have 13:44 no clue that what they're saying is selfish. 13:46 They genuinely think it's best for the organization. 13:48 There's just some misinformation and misunderstanding. 13:50 Because there's a dogmatic aspect of software engineering and it was perpetuated in the previous era into two thousands. 13:57 2000 I when I ventured in working professionals of Engine 2007 8-9, there was a lot of dogma. 14:04 Like there's a lot of this is how you do things and this is how you should do things. And if you do things any other way, you're wrong. And part of that is elegance of code, code cleanliness, code quality. 14:15 You're all raised on this, these these concepts, right? 14:18 And they're important. And everybody always complained about bad code and horrible code because it was difficult to maintain. Nobody enjoys that. 14:24 You're going to make it very difficult for the future engineers to solve these problems. 14:29 But sometimes, you know, you don't have future engineers to solve these problems. Sometimes nobody's going to touch this code for decades to come. 14:37 It's OK if it's just, it just works. 14:40 And then we ended up on the complete other end of the spectrum where we tried to clean up everything that we started adopting all sorts of design overcomplicated abstractions that are are just horrible to read, horrible to reason about. 14:53 It takes you decades to become proficient in just reading that type of code. And then when you write it, it gets even more complicated and it's very difficult to maintain. 15:04 And big tech and I always tell my colleagues and the juniors that report to me, simple is complicated enough, especially at scale. So just write it in the dumbest, most simple way possible. This is why I also love Go, for example as a language. Right. 15:20 It's amazing. It's dumb. 15:22 You don't have to think too much, it's just all in your face. Whenever you want to understand how something is built, just trace it around. 15:29 It's there. It's there, fantastic. 15:32 I love that. And when the situations where we're building at scale, I don't want to reason about abstractions, I don't want to think about edge cases, I don't want to think about complicated memory allocations and complicated memory structures. You know, I just want things to 15:49 be simple. Memory leaks happen often and they are very catastrophic at scale. 15:55 I don't want to think about these things. 15:57 I don't want to think about how my garbage collector is going to, you know, shut down the whole world and start causing multi second latency on my API requests, which at scale again, become a gigantic problem for me. 16:08 I just want things to be simple, easy to reason about and that's it. What is then your perspective on building systems that can evolve? 16:17 Because some people you can say, OK, this is the system designed that we have and we're going to continue on this until we reach a certain level of scale, and then we're going to revamp and say this would be the next iteration. 16:28 But some people also say, OK, we have a system now and this is evolvable to whatever skill we need. 16:34 And then they put in the extra effort to make sure that that is there from the beginning. In our industry, very few technologies last for like a decade plus and the rest is changing often and that's why I personally don't invest or I 16:51 wouldn't design a solution that will last like 1020, thirty years, unlike what we did in the 80s or 90s. 16:57 That's why that's how they that was the design mentality. 16:59 But things were way less complicated than they are today and the scale was different. So I would always come with the mindset that I'm just going to design for the next order of magnitude and then I'm going to evolve it from there. 17:11 And that's going to require another round of investment. 17:14 There's going to be continual investments in this and that. 17:17 Business people are not going to love this because that makes accounting much harder. That makes strategic finance much harder because they cannot predict or anticipate the costs that might come in the future. They cannot extrapolate from today. You know they don't like this 17:31 fuzziness. Of software, it's all risk. 17:34 Yes. So and, and also like they cannot calculate like their bottom line or projections for the future, which are things that are very realistic. 17:40 Like public, publicly traded companies want to be able to do these projections and they want to be able to say that, hey, we're not going to be spending more here in on evolving our software, but we're going to make much more revenue and increase our bottom line and margin. 17:54 That's what businesses look for. So it's understandable. 17:57 But from a software perspective, there's needs to be regular investments. And I think the only approachable way, which is something we do at GitHub is to continuously revisit these investments on a quarterly by quarterly, half a year or a year basis, right? 18:13 We can make projections for the next 3-4, five years, but the confidence in these projections is less and less and less the more time grows and I think a lot more companies need to start doing the same. We're always working in teams. 18:25 Also from a business standpoint, how would I, for example, say we're going to design for this until we reach scale and then we're going to need to revamp? And this is what that's going to entail for people that don't understand how to build software. Understand the business 18:37 constraints. So you're never going to be able to convince the business folks about of something technically. 18:43 They're just. It's too abstract. 18:45 Even if it feels too intuitive for us, for them it's. 18:49 Magic. Yeah. 18:51 And even if they try to understand how things work, they're never going to comprehend the magnitude of problems and they're never going to have have this intuition about how software is and how not hard, you know how how evolvable it is. So it's our job to get closer to 19:07 their side. Some people say, no, we want the business to understand they're not gonna it's trickier. 19:13 It's easier for you to acquire or assimilate some of the not everything, some of the business constraints and discuss them from that perspective. And that's why a lot of engineers who grow are very good at understanding the business 19:26 constraints and then discussing the technical solutions within those constraints. So for example, I used to work in the container terminal industry for a while. 19:35 We built a huge container terminal. 19:38 We furnished everything from the fibre optics layer all the way to the three tier data centre with all of the enterprise applications running, running on it and the operating system for the container terminal. And it's one of the most massive 19:47 operations you can ever imagine, one of the most hazardous as well. So the folks there, they're as far away from tech as possible. You're not never going to find the terminal operator who's going to understand what it means that your database is running hot and you cannot 20:04 support their keys. All they care about is, I have a ship here who's docked. There's like 10,000 containers on it. I need to empty them into my yard. I have a very fixed window of time and if I don't do it in that window of time, this is 20:17 going to cost me money. We were operating at 12% capacity. That terminal was generating about $50,000 per hour, so 12%. So you can imagine if we get delayed, every minute of delay is actually money that's disappearing. So this is how you need to 20:37 discuss problems with and and investments and solutions. 20:41 You need to understand what the impact is, what the impact is on the operators. And sometimes it's life threatening impact, right, If your software fails when ASTS, when the crane is offloading a container, this can be a very 20:55 life threatening situation. You cannot really have your software malfunction at these points. 21:00 So snappiness of the software, sub millisecond latencies, all of these things matter, right? So you need to approach the discussions with the stakeholders by understanding them first. So what I've done for example, in that industry is I've literally sat on a truck and 21:16 went there and I sat with every single individual who works in that terminal to really understand what they go through on a daily basis. So a truck driver who's driving a truck for a six 7-8 hours and it was in Saudi Arabia in 21:27 scorching heat is not going to understand why the button that they clicked is just is so slow. Doesn't matter. 21:35 Doesn't he doesn't care, right? He just wants it to just work. 21:38 So you got to understand all of these perspectives and then when you do, you can start approaching discussions from that vantage point. And this applies to banks, this applies to hospitals, to any other industry. 21:48 So understand the industry, understand the business constraints, and then any technical solution you want to discuss an investment, you can approach it from that vantage point and you're going to have much more success in these conversations. When you were speaking about 22:01 hard skills, how much of enterprise architecture or being an architect in essence has changed nowadays? 22:08 Because I feel like I get bombarded with tools. 22:11 There's a lot more possible, specifically with large language models, but in essence, like the Phantom sketch Artist, everything underneath kind of still holds true. 22:20 From your perspective, does architecture evolve quickly? 22:24 Because I feel like tooling does at a more rapid. 22:26 Pace, definitely the environment in which you operate has changed. So there's a couple of assumptions that architects used to be able to make to make their lives easier that no longer hold right. 22:39 And the one is like snapshotting, like the world is moving too fast to be able to pretend. 22:44 It's like, OK, let's just assume nothing changes. 22:47 Well, that turns out to be a very poor assumption in today's environment. So that, for example, means exercises like trying to draw a giant ID landscape, you know, or cataloguing all the applications you have and putting that into some tools. Taking a few months for that, 23:04 yeah. And then a few months, by the time you're done, this has already changed. 23:07 So for me, the assumption of being able to snapshot and being, I call this the cartographer, being the person who makes all the great landscapes, that is very useful, but it's no longer practical because stuff changes too quickly. So one of the metaphors I use 23:23 which captures the change in role for Enterprise Architects is rather than trying to be the cartographer who walks around with a giant map of all the pieces, you need to be much more like a scout. You have a objective in mind. 23:38 You want to cross the river or beat the enemy or like move somewhere or like whatever, right? 23:42 You have some objective, you send some scouts, right? 23:45 They're going to go look at things. 23:47 They figure out what works, what won't work, right? 23:50 And they come back to you with a very simple map, but a very timely and very expressive map, right? 23:56 So you want to cross the river. It's like, oh, here's the mountain, here's the enemy, the bridge is gone, but here's not so deep. We can cross there, we can go around whatever it is, right? But they have a very situational, they have a sort of purpose driven map. 24:08 The map is not trying to be like the perfect map of all the exact landscape. They only depict what's it's relevant to your move and I think that is becoming a more viable metaphor. What enterprise architects should do. It's no longer plausible to like 24:27 maintain this giant map where everything is on and everything is up to date. Rather you need to have a purpose. You need to have a direction of mind. Like LLMS Gen. 24:38 EI is a great example. I don't get de enterprise architects, what's our strategy for this? 24:43 Where should we find the best first use cases? 24:45 How do we integrate this with the rest of our system? 24:47 We know LMS have super high rate of evolution, right? 24:51 So how do we keep that change out of other systems, right? 24:55 What are we doing with with Agents and Agentec, right? 24:58 Is that just another form of workflow integration or is that something novel, right? Give me a point of view. 25:04 But it's very purpose driven. And as you will quickly see, you can only do that if you understand the subject matter, right? You can sort of arm wave your way through that, right? You need to have, you know, the hard tech skills as well. But for me, it's very purpose 25:20 driven. What should we do? 25:22 Do we have a point of view, right? 25:24 Do we have a question in mind? Too many architects try to find answers when they don't have a question. 25:30 And so it's like, oh, here's the thing that answers all possible questions. I'm like, that would be nice. 25:37 Wouldn't that be, wouldn't that be easy? 25:39 That doesn't work anymore. You got to start with a question in your mind. And then like the scout, I was like, whatever, can we cross the river? 25:47 I was OK, come back with the answer to this. 25:49 It's got to be situational and timely. 25:52 Otherwise it becomes hard work. And we might like our hard work, but I always say we're not a museum. 25:58 We're the IT you. Can't be a historian, yeah. 26:00 Exactly. We can't be a historian. 26:02 We're not collecting modern art, right? 26:04 Our diagrams serve a purpose, right? 26:06 They help us make better decisions, get a better decision, Transparency and discipline. 26:11 So a the decision is is clearer and everybody's on the same page to what the decision was actually what drove the decision. What trade-offs are we willing to make? That's what adding the value and that the picture just has to be a means to that end. 26:27 If that end isn't there, the pictures also worthless. 26:30 Then it just becomes modern arts and boxes and triangles and kind of kind of things. From a career perspective, people are saying very early on, topics are getting automated now by agents, which means that the people that are educating 26:43 themselves and that usually that's a step for them to build up the skills to do very, very cool things that help society. 26:50 That step is now changing and people are asking, well, what do I do then to make myself not obsolete? 26:54 And we're talking about anything with regards to communication and soft skills and learning. I agree with all of that. 26:59 And then there's still a tooling aspect. 27:01 Like I don't know what I should advise people with regards to, OK, how do you go from junior to actually in the end becoming senior? Because it's such Gray area that I don't know yet. I feel like we're really figuring things out. And the only advice that I have 27:14 is be as open minded as you can. Try and familiarize yourself with a lot of things. Try and build as much foundational knowledge as you can because tooling does change. 27:23 I'm wondering what your perspective is on that. 27:26 Don't be a fool with a tool. That is one of the core pieces of advice I got started my career over 9 years ago. 27:36 God, don't be a fool with a tool. 27:40 Back then we refer to only knowing our only knowing Python or only back then. Do you remember RPA people? 27:47 Do you remember back when RPA was a was a thing? 27:51 I was using a Python package back back in the day to to scrape Twitter. I forgot forgot the name Selenium. Yeah, yeah. 27:59 I was learning Selenium because that was one of the first Python based browser. This automate the browser and click down. Back then those were bots, but I knew people who doubled down on only learning Selenium and all the insurance and outs. But Selenium was open source and 28:17 it was great. You could do everything with it. 28:18 But then the blue prisms came in, which was basically the the company or the company organization equivalent of it. 28:27 But it was reliable because you could sue somebody if it didn't work. And suddenly the whole Selenium market disappeared because people went for for larger infrastructure tools instead. And the guy who knew everything about Selenium was stuck and the people who learned Blue Prism 28:42 were laughing at him. Nowadays we laugh at the people who only know Blue Prism because the cycle continues. 28:48 It's not about learning anyone tool, it's about being able to learn in general. And that involves learning the insurance and outs of tools. I think it we are switching from an explicit knowledge economy to an implicit knowledge economy 29:07 and our education systems haven't adjusted to that, that the worth of knowing stuff in your head, memorizing it, that worth is only going down. But the ability to look up stuff that was introduced like what, 25 years ago when Google hit the 29:23 market, before we had that, we had start start that has been introduced during our lifetimes. But the value of that, of finding stuff in large amounts of information, that is only going up, especially in the age of disinformation, because we 29:41 are drowning in information. But truth and wisdom has only increased invaluable and has become relatively more scarce because now there's more bots and more fake stuff flooding the Internet than actual real stuff. And the only way we can still 30:00 distinguish truth from fake, because I see so many deep fakes now of Zelensky, of Putin, of F-30 fives that crashed in Iran. 30:08 And we could only tell they were fake because there was still a a human in the cockpit, because they forgot to prompt it remove the human from the cockpit. We can only tell truth from fake because of human error. And that too will end. 30:22 So what we need to learn, again, because learning is important, is to triangulate information to figure out what's real. 30:28 And This is why I I'm frustrated with modern media and journalism that thinks that just regurgitating and repeating what no liar say is somehow journalism. 30:38 I forgot the quote, but somebody once wrote this. 30:41 If one source tells you it's raining and the other says there's sunshine, your job as a journalist is not to report both, but to open a damn window. And that's what I'm missing. 30:53 What is your perspective on AI tooling in this building frame? 30:57 Because if you're looking towards end goals, if my end goal is to build a product or an e-commerce website, I can, I can generate a lot of that stuff. But would I then learn how to actually do that? No, I would achieve my goal in a different manner. Would people from your 31:10 perspective that Start learning now? 31:12 Should they leverage AI tooling or how can they use it to learn effectively? That's a great question and we're still finding that out. I think so. 31:22 So my take is yes, you can use it to to set up a lot of things for you. I would more use it as a tool for validation rather than something for, for you to generate things right. So if you are not able to actually explain what comes out of this model and, and if you 31:43 are not able to understand why the code is there, then you will have a very rough problem also maintaining that and extending that. And of course then you can say, OK, well, then I have some agents, AI agents do that for me. But ultimately there, there's, 31:58 there will be a gap of understanding where the model trips up and, and you are not able to get it, catch it. 32:04 So use, use AR models to validate your understanding, try to generate maybe a few things and see, do I actually understand what's happening here and not ask the model right that that's great. But don't focus on on getting a 32:20 polished product out of it and then getting sort of the, the, yeah, the products there. In the end, it's, it's really a tool that you can use, especially if you're like taxi driver who's who's going to learn coding. 32:34 It's a tool that you can use to, to build your knowledge. 32:37 You can also use very much to cheat, of course, and to just sidestep all of this hard work of, of trying to understand it. 32:44 But I don't think that will in the long run help you.
Community discussion