WEBVTT 1 00:00:06.360 --> 00:00:10.560 Hello, Welcome to React Round Up, the podcast where we keep you updated 2 00:00:10.640 --> 00:00:16.679 on all things React related. This show is sponsored by Raygun and produced by 3 00:00:16.920 --> 00:00:20.679 Top and Devs and Onvoid. Top and Doves is where we create top and 4 00:00:20.719 --> 00:00:24.800 devs so get top and pay and recognition while working on interesting problems and making 5 00:00:24.839 --> 00:00:30.960 meaningful community contributions. An Onvoid provides remote design and software development services on a 6 00:00:31.000 --> 00:00:37.600 performance basis, so clients only pay after the tasks are delivered and approved. 7 00:00:38.240 --> 00:00:43.960 In today's episode, we will talk about artificial intelligence in the day to day 8 00:00:44.000 --> 00:00:50.479 life of a React developer. That is going to cover using AI tools to 9 00:00:50.520 --> 00:00:55.479 help you generate codes such as copilot, but also tools that are going to 10 00:00:55.520 --> 00:01:00.280 turn the designer files into a first version of the so that you can iterate 11 00:01:00.359 --> 00:01:07.480 later. My name is Lucas Paganini. Your host in a podcast. Joining 12 00:01:07.480 --> 00:01:14.239 me in today's episode is Chris Ruin, Hi everybody, and Peter Ossa. 13 00:01:15.719 --> 00:01:21.239 Hi, E one. All right, let's get to it. So, 14 00:01:21.319 --> 00:01:26.920 Peter, Chris, I think my first the first thing that I like to 15 00:01:26.000 --> 00:01:33.920 understand is what row is artificial intelligence playing in the lives of both of you 16 00:01:34.200 --> 00:01:38.799 at the moment, Like, how much are you currently already using AI for, 17 00:01:40.239 --> 00:01:46.280 Which tasks are you not using AI for? And what things you haven't 18 00:01:46.400 --> 00:01:52.159 used yet but you are definitely considered doing. It makes sense, So basically 19 00:01:52.560 --> 00:01:57.920 just a summary, what are you currently using AI for, what you are 20 00:01:57.959 --> 00:02:01.000 not but you are considering you just haven't had a time, and what you're 21 00:02:01.120 --> 00:02:07.760 just definitely not going to even try to use AI for. So maybe Peter, 22 00:02:07.000 --> 00:02:13.400 would you like to start Okay? Yeah, so yeah, yeah, 23 00:02:13.479 --> 00:02:16.479 is actually a very important, very useful to I as a developer, Like 24 00:02:16.599 --> 00:02:23.319 I kind of reli on AI for most of my work. Now what it 25 00:02:23.560 --> 00:02:27.479 is actually very important to me is in the aspect of knowledge, right, 26 00:02:27.599 --> 00:02:31.879 So I'm a fan of actually, okay, using the EI to kind of 27 00:02:32.439 --> 00:02:38.919 get some ideas that I don't have. That's maybe some knowledge that I am 28 00:02:38.960 --> 00:02:44.560 true less about. So just for example, I see a strange method maybe 29 00:02:44.639 --> 00:02:49.479 yeah, well working with it like it could be and I see maybe it 30 00:02:49.639 --> 00:02:52.879 kind of a new method, and I'm like, oh, I don't know 31 00:02:52.879 --> 00:02:57.680 what this is, and maybe I have no clue. Now, usually in 32 00:02:57.719 --> 00:03:00.800 the past we start going to yeah, obviously it doesn't admit you within the 33 00:03:00.840 --> 00:03:06.319 dogs, but you start going to start overflow to see its use starts using 34 00:03:06.479 --> 00:03:09.360 the Google and checking other places. Right. So what I do in then 35 00:03:09.400 --> 00:03:14.960 is something that does when usually charge you to be a cloud, right, 36 00:03:15.039 --> 00:03:20.639 it does give me like a kind of description like details, does a small 37 00:03:20.719 --> 00:03:24.520 idea of the of of photose functions are or what those methods are. Right, 38 00:03:24.879 --> 00:03:29.400 So it's kind of helpful to just it's just like I'm assistant, right 39 00:03:29.479 --> 00:03:32.439 for me in the sense that it's it's for me like a knowledge bank. 40 00:03:32.560 --> 00:03:37.800 Right. So if I don't have an idea of things, I use that 41 00:03:38.240 --> 00:03:42.840 now. One thing I don't use AI to do is kind of I don't 42 00:03:43.199 --> 00:03:46.520 let a kind of replace my thinking ability, right to because I think that's 43 00:03:46.599 --> 00:03:51.000 the aspect that a lot of people kind of hope with it to and be 44 00:03:51.000 --> 00:03:54.360 like, oh, you're working in you're working on you're working on a code 45 00:03:54.360 --> 00:04:00.039 base, and you'll be like, oh, generate this to do this and 46 00:04:00.159 --> 00:04:01.960 you just learn on the code on they are. Yeah, in the long 47 00:04:02.039 --> 00:04:05.479 grown, Yeah, you'll be efficient on just re both in the long grown. 48 00:04:05.520 --> 00:04:11.960 If you're not really learning anything new, let's assure if or the challenge 49 00:04:12.039 --> 00:04:15.840 is something that requires you to learn something, right, you're just accidental? 50 00:04:15.879 --> 00:04:19.120 Are you just generate it for you? And you just use so for self 51 00:04:19.120 --> 00:04:26.800 development, willing not the best like for especially for going developers as well, 52 00:04:26.839 --> 00:04:30.519 like if you're starting out with the menially bad at always here, if you're 53 00:04:30.519 --> 00:04:33.600 starting out because you need to learn, need to just learn the basics, 54 00:04:33.639 --> 00:04:39.319 and you need to actually learn and practice with the basics, right, So 55 00:04:39.600 --> 00:04:44.240 I usually I just more like an assistant too, to assist me in giving 56 00:04:44.240 --> 00:04:46.759 me insights about settings. I don't know. I also use it to kind 57 00:04:46.759 --> 00:04:51.879 of an interactic sation or is there an application of this? Can I how 58 00:04:51.920 --> 00:04:55.759 can I use this in this kind of code base? Yeah, will you 59 00:04:55.759 --> 00:04:58.680 get the ideas, then you can always kind of modify the idea. So 60 00:04:58.800 --> 00:05:01.759 I think that's just how I use Yeah, I don't know if that answers 61 00:05:01.759 --> 00:05:06.160 your question. Yeah, it does make sense. I'm not sure if there 62 00:05:06.240 --> 00:05:12.079 is a right or wrong answer. Is definitely how you're seeing it, So 63 00:05:12.800 --> 00:05:17.279 I think it I could really understand the applications that AI has in your day 64 00:05:17.279 --> 00:05:20.759 to day So I think, yeah, it made total sense to me. 65 00:05:21.079 --> 00:05:25.199 How about you, Chris? Yeah, so I think I'm quite similar to 66 00:05:25.279 --> 00:05:30.199 Peter so me personally, I have I do have a subscription to Copilot, 67 00:05:30.800 --> 00:05:36.959 happy to pay for that. It's been it's been working quite well. And 68 00:05:38.120 --> 00:05:44.920 I do use chat GPT sometimes, I guess, so those are the two 69 00:05:45.000 --> 00:05:54.199 main tools I use. Just yesterday was experimenting with Google's Gemini, the new 70 00:05:54.240 --> 00:05:58.040 Gemini AI, so just just trying to see getting a feel for how it 71 00:05:58.040 --> 00:06:05.639 compares to Open AI stuff. And I guess so I'm I'm fairly agnostic. 72 00:06:05.879 --> 00:06:11.000 I don't know yet. I don't have enough experience to say if there's a 73 00:06:11.040 --> 00:06:15.839 tool I guess I wouldn't use. But for me, it's more it's more 74 00:06:15.920 --> 00:06:20.800 just a function of time and and workflow that I'm used to. So I 75 00:06:20.920 --> 00:06:23.920 you know, I've been developing for a while. Now, I know my 76 00:06:24.000 --> 00:06:27.800 tools, and it's just a matter of saying, okay, you know does 77 00:06:27.839 --> 00:06:30.560 this you know, for example, you mentioned Lucas, there's there's tools that 78 00:06:30.600 --> 00:06:36.759 can generate perhaps designs just from Pigma files and stuff that could be very advantageous. 79 00:06:36.759 --> 00:06:40.199 But I just I don't have the time, I haven't explored it. 80 00:06:42.759 --> 00:06:47.800 So I guess yeah. More as to how I guess, I use them, 81 00:06:48.639 --> 00:06:53.480 and I think Peter pointed to a good point which I'm guilty of forgetting, 82 00:06:53.560 --> 00:06:57.759 is that I think we're so used to at least recently. We're so 83 00:06:57.839 --> 00:07:00.160 used to thinking of AI as it just generates, It just produces stuff, 84 00:07:00.199 --> 00:07:05.079 stuff, stuff stuff. But what I forget a lot is that in a 85 00:07:05.120 --> 00:07:11.120 new code base you can throw in functions and classes and say like, hey, 86 00:07:11.240 --> 00:07:14.879 what's going on here and get a nice overview without you know, maybe 87 00:07:14.879 --> 00:07:18.519 pouring over five hundred thousand lines of code. So that's something that I think 88 00:07:19.959 --> 00:07:29.040 for for anyone using AI, that's something that you shouldn't forget. And yeah, 89 00:07:29.120 --> 00:07:33.519 that's that's uh, I guess that's yeah. Again, I also don't 90 00:07:33.560 --> 00:07:35.959 know if I answer your question. That's that's kind of how I how I 91 00:07:36.000 --> 00:07:43.040 see it, okay. Uh. And actually, one thing that I am 92 00:07:43.079 --> 00:07:47.439 going to recommend for anyone who is already using Copilot or any other similar tool, 93 00:07:48.199 --> 00:07:54.000 is there are ways for you to kind of like when you're talking to 94 00:07:54.120 --> 00:08:00.000 chat GPT, you create contexts before you start asking the things you really want. 95 00:08:00.519 --> 00:08:03.800 So let's say that you are looking for another job and you want help 96 00:08:03.920 --> 00:08:09.759 to review your resume. You're going to have some initial chat with the AI 97 00:08:11.319 --> 00:08:16.439 just explaining who you are, what do you want in your resume, to 98 00:08:16.519 --> 00:08:22.240 which positions you're most interested in applying to. So you're going to create this 99 00:08:22.360 --> 00:08:28.079 initial context before you start asking the AI to answer your questions, right, 100 00:08:28.160 --> 00:08:33.200 and with code we can also do that. And the way that we can 101 00:08:33.240 --> 00:08:39.279 do that is well, of course, your entire code base is already context 102 00:08:39.519 --> 00:08:46.000 for the artificial intelligence. Like many many of those AI code writers are going 103 00:08:46.080 --> 00:08:50.679 to consider the context of your application, like is it a React application and 104 00:08:50.720 --> 00:08:58.000 Angular application? How is how are the other developers structuring the code? Those 105 00:08:58.039 --> 00:09:03.200 tools are going to consider that. But one thing that you can do to 106 00:09:03.240 --> 00:09:07.480 give explicit instructions because some maybe you're worried about that, like I don't want 107 00:09:07.519 --> 00:09:11.759 the artificial intelligence to consider the rest of the cobase because the rest of the 108 00:09:11.759 --> 00:09:15.759 cobase is like very messy and I want to do something different, I want 109 00:09:15.799 --> 00:09:18.559 to reflector so it should not considered just that. So what you can do 110 00:09:20.440 --> 00:09:24.600 is document your style guide. You know, you can just have a style 111 00:09:24.639 --> 00:09:31.320 guide dot mb file at route and be very very explicit about every single convention 112 00:09:31.840 --> 00:09:35.639 and best practice that should be used in that code base, even if they 113 00:09:35.679 --> 00:09:41.720 are not being used yet, and that is going to serve as material for 114 00:09:41.879 --> 00:09:48.200 the artificial intelligence that you're using to know what style of code to generate. 115 00:09:48.799 --> 00:09:54.799 So that's kind of like a quick hot tip for all of you using those 116 00:09:54.879 --> 00:09:58.720 tools. Well maybe not quick, because you still got to write the style 117 00:09:58.759 --> 00:10:03.919 guide. Yeah, it's It's something that I think some teams don't worry too 118 00:10:03.000 --> 00:10:09.159 much about because they think, oh, like the developer, where we don't 119 00:10:09.159 --> 00:10:13.039 have developers joining this project, like there's no reason for us to stop and 120 00:10:13.080 --> 00:10:16.720 document the style guide. But there actually is, because that's also input material 121 00:10:16.840 --> 00:10:24.120 for artificial intelligence and also for every other developer that joins the project later on. 122 00:10:24.639 --> 00:10:30.519 So yeah, I wonder if you guys have any other chips or tricks 123 00:10:30.639 --> 00:10:37.320 that you use to kind of fine tune the AI to make sure that it 124 00:10:37.399 --> 00:10:41.080 is going to produce code that you're actually going to use. Well, yeah, 125 00:10:41.240 --> 00:10:45.600 on my end, what I do. I don't know if I have 126 00:10:45.799 --> 00:10:50.000 like a peculiar technique too, but I usually try to engage in discussion. 127 00:10:50.080 --> 00:10:54.519 Like you said, start with the premise, will give this is, don't 128 00:10:54.519 --> 00:10:58.559 point this is what the problem is? This don't find be like an intellectual 129 00:10:58.639 --> 00:11:03.279 way. I think we get to point whereby I kind of write some kind 130 00:11:03.320 --> 00:11:05.480 of commands, right, I think you also put it in the way for 131 00:11:05.519 --> 00:11:09.399 example, if I'm actually writing. Maybe I also just get an idea or 132 00:11:09.399 --> 00:11:13.279 something in the text, I put it in maybe human readable format. I 133 00:11:13.320 --> 00:11:16.919 think that would be the point. Or I want this to be human re 134 00:11:16.960 --> 00:11:22.159 double format so that it can be understood by someone with maybe minimum knowledge a 135 00:11:22.200 --> 00:11:26.639 party subject. Same thing with code as well. Just okay, I don't 136 00:11:26.879 --> 00:11:31.879 you can I could just maybe put it to bad functions or use the fundamental 137 00:11:33.120 --> 00:11:39.399 like maybe just committees on the edge, do not use maybe things like some 138 00:11:39.480 --> 00:11:43.519 higher other functions like I'm using Java spets to like maybe if I have like 139 00:11:43.600 --> 00:11:48.200 a could stuff. So I think there's are also that I do as just 140 00:11:48.519 --> 00:11:52.559 belable from Marth those format it in the way there's kind of low level so 141 00:11:52.639 --> 00:11:56.320 that someone who is a beginner can understand and so on. Yeah, not 142 00:11:56.480 --> 00:12:01.639 really much though, and also I don't know. I usually, especially for 143 00:12:01.840 --> 00:12:07.519 company projects, I guly tried to avoid putting company data into the equal because 144 00:12:07.559 --> 00:12:11.919 I think there was an issue when I don't know if it's from amazonaway there 145 00:12:11.000 --> 00:12:16.279 was a leak of setting company data due to I think I think it's from 146 00:12:16.519 --> 00:12:18.120 charge you TPOs, so I think there was a use about that. So 147 00:12:18.240 --> 00:12:22.480 I gently tize to avoid us putting company logic or data. I just put 148 00:12:22.480 --> 00:12:28.879 it out about logic just because of I could get like ideas. Yeah, 149 00:12:28.120 --> 00:12:33.919 so what do you do as a christ? Yeah? I guess, I 150 00:12:33.919 --> 00:12:37.360 guess. One advice I would have is that you have to be specific. 151 00:12:37.480 --> 00:12:43.200 Right, So it's it's just like the whole you know, manager specification joke 152 00:12:43.279 --> 00:12:46.320 that we all know as as devs. If you just say, if you 153 00:12:46.360 --> 00:12:50.159 go to any of these generators and say, hey, make me a button, 154 00:12:50.360 --> 00:12:52.440 you could, I mean you can. Yeah, okay, you specify. 155 00:12:52.480 --> 00:12:56.480 Even if you specify React, make me a React component button, you 156 00:12:56.519 --> 00:13:03.159 can get who knows five hundred different things? Right, So you it's it's 157 00:13:03.200 --> 00:13:07.799 best to you know, I typically specify, like you know, I want 158 00:13:07.840 --> 00:13:11.159 to React type script. You know these props. Uh, you know, 159 00:13:11.240 --> 00:13:16.480 be as specific as you can. And if you if you can't be specific, 160 00:13:16.480 --> 00:13:20.360 well then maybe, you know, maybe you need to even think about 161 00:13:20.679 --> 00:13:24.360 what what your feature is or what what you're building at the moment. Otherwise 162 00:13:24.399 --> 00:13:30.600 you can get just as much junk out as as as you want. So 163 00:13:31.519 --> 00:13:35.600 yeah, yeah, that does make sense, And it's what you would expect 164 00:13:35.720 --> 00:13:43.480 interacting with a real person, right. You can't just give very little instructions 165 00:13:43.519 --> 00:13:48.039 and expect the other individual to really do exactly what you had in your mind, 166 00:13:48.080 --> 00:13:52.440 You're going to have to properly describe it. So yeah, I think 167 00:13:52.480 --> 00:13:56.960 that that does make a lot of sense. And quite frankly, I don't 168 00:13:56.960 --> 00:14:01.480 think most of the issues that are generally document it in a project are good 169 00:14:01.559 --> 00:14:07.120 enough for an artificial intelligence to understand. I don't know about you, guys, 170 00:14:07.159 --> 00:14:15.000 but I've spent quite a few time like trying to understand what the creator 171 00:14:15.039 --> 00:14:18.759 of the issue actually wanted me to do. So if I were to just 172 00:14:18.799 --> 00:14:22.279 throw that to an artificial intelligence, I would be really surprised if it would 173 00:14:22.639 --> 00:14:28.879 if you were able to really understand what has to be done. So yeah, 174 00:14:28.960 --> 00:14:35.559 yeah, that makes doutal sense. What about like things that you are 175 00:14:35.600 --> 00:14:41.879 considering to explore, Like, of course we have those generators right from figma 176 00:14:41.919 --> 00:14:48.960 to code, but is it something that you guys really think is ready to 177 00:14:50.480 --> 00:14:52.279 test and ready to try out? Because I got to be honest, like 178 00:14:52.440 --> 00:14:58.720 I'm a bit skeptical. You know, I haven't even really stopped to see 179 00:14:58.879 --> 00:15:03.679 thelity of the code that is produced by those generators, because every time I 180 00:15:03.759 --> 00:15:09.519 saw somebody making a video about the code that was generated, it was always 181 00:15:09.600 --> 00:15:15.159 like terrible. So it was like cool at first, but then it generated 182 00:15:15.200 --> 00:15:20.440 some stuff that was like either completely different from what it was supposed to do 183 00:15:22.120 --> 00:15:28.039 or just like the code itself was just really not using modern best practices, 184 00:15:28.120 --> 00:15:33.720 you know. So because of those videos of other creators are very talking about 185 00:15:33.720 --> 00:15:37.360 this, I kind of don't even feel the need to test it out myself. 186 00:15:39.080 --> 00:15:41.480 But I don't know, maybe I'm missing out on something really interesting, 187 00:15:41.480 --> 00:15:48.279 you know, maybe there is a tool that is pretty awesome at doing this 188 00:15:48.840 --> 00:15:56.120 figma to code transition already, and maybe I am just a dinosaur, you 189 00:15:56.159 --> 00:16:00.320 know, and I haven't tried it out yet, so I don't know. 190 00:16:00.519 --> 00:16:07.519 Are you guys also skeptic about this or do you think that there are indeed 191 00:16:07.720 --> 00:16:12.320 tools that might be already good enough for this. And by the way, 192 00:16:12.440 --> 00:16:17.799 I'm really sorry about this because I really wanted to be here to listen to 193 00:16:17.879 --> 00:16:22.320 your answer for this, but I will have to watch you later on because 194 00:16:22.440 --> 00:16:25.919 I actually have a personal commitment, so I'm going to have to bail the 195 00:16:25.960 --> 00:16:30.720 show now. But but yeah, I'm I'm sure the audience is going to 196 00:16:30.799 --> 00:16:34.399 be fine, like they are in very good hands. But yeah, let 197 00:16:34.399 --> 00:16:38.720 me know what your thoughts are on this and I'll make sure to watch you 198 00:16:38.799 --> 00:16:45.240 later. Chris Peter, thank you all right, Lucas take care. Yeah, 199 00:16:48.720 --> 00:16:52.840 yeah, I think I think I'm kind of in a similar boat. 200 00:16:52.200 --> 00:16:57.720 I am quite skeptical, but I think it may even come down to just 201 00:16:57.919 --> 00:17:04.319 language and itself, because you know, going back to this concept like make 202 00:17:04.400 --> 00:17:08.240 me a button, you can even be even if you do something more specific. 203 00:17:08.279 --> 00:17:12.799 I ran into this was one of my first experiences kind of you know, 204 00:17:12.880 --> 00:17:17.599 poking fun at at chat geep Chan said hey, it's wrong, it's 205 00:17:17.640 --> 00:17:22.799 wrong. But I realized maybe that I was wrong or not specific enough. 206 00:17:22.799 --> 00:17:25.559 So I, for example, you can say, you know, give me, 207 00:17:26.559 --> 00:17:30.000 I guess we'll stay in jobscript, give me a typescript function that compares 208 00:17:30.000 --> 00:17:33.359 to a rays all right. So what it did was I think it just 209 00:17:33.400 --> 00:17:41.480 did Ah. It just checked every every element index by index. Right, 210 00:17:41.519 --> 00:17:45.720 So if the first one first off, they're the same link and then if 211 00:17:45.759 --> 00:17:49.440 each element in each position is the same. But is that does that mean 212 00:17:49.599 --> 00:17:55.519 the arrays are the same in this case? Is it's like what the same 213 00:17:56.640 --> 00:18:00.240 or comparing arrays really mean? And and when you start going down that rabbit 214 00:18:00.279 --> 00:18:04.680 hole that starts to become a whole question of you know, for a design 215 00:18:04.720 --> 00:18:11.279 team, like what really it's It's like, what it is the language behind 216 00:18:11.960 --> 00:18:18.640 our design, our product that all this, I guess this contextual knowledge that's 217 00:18:18.799 --> 00:18:25.960 very hard to put into a text box, right you know what does Yeah, 218 00:18:26.039 --> 00:18:29.000 just even like just small words like what does this mean? The team? 219 00:18:29.160 --> 00:18:32.920 Your team probably knows because you've been working on this this product or these 220 00:18:32.960 --> 00:18:37.119 components or whatever, but uh, you know, chat GBT or Gemini or 221 00:18:37.119 --> 00:18:41.759 whatever doesn't really know. And I think then then what comes into play is 222 00:18:41.799 --> 00:18:47.079 this whole context window. And Lucas was mentioning that that you can kind of 223 00:18:47.559 --> 00:18:52.400 pre treat the output. But unless you're willing, you know, as an 224 00:18:52.519 --> 00:18:56.359 organization to more or less pace your whole code base there, which you know 225 00:18:56.559 --> 00:19:03.200 could be dangerous for some organizations or not desired, then yeah, then I 226 00:19:03.200 --> 00:19:07.880 think you'll have some trouble. And even then, I've I've tried to do 227 00:19:07.920 --> 00:19:11.119 those pre treating It does work sometimes, but once you get I mean I've 228 00:19:11.200 --> 00:19:15.160 I've been just using the three point five so it has a smaller context window. 229 00:19:15.200 --> 00:19:19.960 But even then, once you've you've provided a lot of similar code, 230 00:19:21.680 --> 00:19:26.200 it can still mess up. Just because yeah, I mean it's coding is 231 00:19:26.200 --> 00:19:30.480 hard, I think even for an AI so yeah, yeah, yeah, 232 00:19:30.599 --> 00:19:36.599 that's autually dumble things. Actually, so for genuitos like for figmat to code 233 00:19:36.720 --> 00:19:41.319 designs. Yeah right, I think the one I'm kind of it is enthusagic 234 00:19:41.440 --> 00:19:44.960 about is the BWD out the one I think built out of IQ. I 235 00:19:45.000 --> 00:19:49.680 think the one that actually converts figmat So yeah, components cool. Yeah, 236 00:19:49.720 --> 00:19:59.400 so it's something I actually want to try because I've done some demos. Yeah, 237 00:20:00.039 --> 00:20:03.960 because of it. And yeah, the code and the code generation is 238 00:20:03.000 --> 00:20:07.720 a bit better this compared to some other ones of scene as well. White 239 00:20:07.839 --> 00:20:11.920 so it's a bit better. Let me just say, and I think they 240 00:20:11.920 --> 00:20:17.359 are better. They are better explanations why they could It's actually that way, 241 00:20:17.400 --> 00:20:22.400 I think, right, So, so I think that's actually when I do 242 00:20:22.480 --> 00:20:26.160 want to but over our door, I won't really like for the other generators 243 00:20:26.160 --> 00:20:30.039 of saying, yeah, the code could be messy. Best of all, 244 00:20:30.480 --> 00:20:36.200 they don't. They just they don' don't follow like big partices like oh, 245 00:20:36.799 --> 00:20:41.519 for example, like you said, you're trying to compare maybe a compare array 246 00:20:41.599 --> 00:20:45.720 or an object, and then it's kind of doing some kind of expensive corpulations, 247 00:20:47.000 --> 00:20:53.400 right, maybe so expensive, like and it may not be optimal for 248 00:20:53.480 --> 00:21:00.400 your could like it's not may not be optimal like for memory in especially we 249 00:21:00.400 --> 00:21:03.599 were working with Javasket, which were kind of I won't say it's limited, 250 00:21:03.680 --> 00:21:08.400 but we work with browsers and with limited environments. Is splitly limited memories at 251 00:21:08.400 --> 00:21:11.359 the point, so it's not like I suld we have all the memories are 252 00:21:12.240 --> 00:21:17.640 so us kind of so right, So yeah, so that's for that as 253 00:21:17.640 --> 00:21:21.400 well. Then the code structure the way it's been with it, Yeah, 254 00:21:22.000 --> 00:21:23.799 I don't know if they just look kind of clank in my eyes. I 255 00:21:23.960 --> 00:21:29.519 really don't know why. It just looks too jumped off like right, So 256 00:21:29.960 --> 00:21:33.480 if you it's something that, Yeah, the it's the code. The elements 257 00:21:33.480 --> 00:21:37.279 of the code kind of takes a lot of like I want to say Boz 258 00:21:37.440 --> 00:21:42.480 was of big functions and just piece it around out so qu too. Yeah, 259 00:21:42.720 --> 00:21:47.359 so far I think code quality wise. And then the output, yeah, 260 00:21:47.400 --> 00:21:49.920 I've seen some of them. The output could could be nice for setting 261 00:21:51.039 --> 00:21:55.960 designs whereby it try it gives you I think almost piece of perfect designs. 262 00:21:55.960 --> 00:22:00.160 But there's this something I see as well that it's kind of off like think 263 00:22:00.160 --> 00:22:03.720 I also see generators like Setta in the ears, I try to kind of 264 00:22:03.759 --> 00:22:07.440 like build like a software, like a small sUAS product in in a few 265 00:22:07.480 --> 00:22:11.559 seconds, and you'll be like, oh, give it some discussion. I 266 00:22:11.599 --> 00:22:15.039 just needed to build this application for me, for example, build like a 267 00:22:15.079 --> 00:22:21.920 rider application and so on, and then it's kind of the output is kind 268 00:22:21.920 --> 00:22:26.519 of not nice. It's not something presented at all, like it's actually far 269 00:22:26.559 --> 00:22:32.319 from the desired output to right. So yeah, I'm I'm really yeah. 270 00:22:32.799 --> 00:22:37.400 Most for the ones of so far generators, they are really not like I'm 271 00:22:37.400 --> 00:22:41.119 not, I won't say they are. They're actually improving as well. But 272 00:22:41.240 --> 00:22:45.559 then I'm most in anyone that is actually kind of so it's so fascinating, 273 00:22:45.720 --> 00:22:49.039 except mably, I do want to want to try which is boed as bidous 274 00:22:51.359 --> 00:22:53.160 generator. I think fiedmach cool. I think I just want to try that 275 00:22:53.240 --> 00:22:59.039 then give my opinion. Yeah, I think I'm in the in the same 276 00:22:59.079 --> 00:23:02.160 boat. I do want to try these tools, but like I mentioned before, 277 00:23:02.160 --> 00:23:04.599 it's just a matter well, first of time, I need time to 278 00:23:04.960 --> 00:23:11.119 try them. But I think they're they're quite interesting. It's interesting you mentioned 279 00:23:11.119 --> 00:23:17.359 builder dot io because just yesterday I was reading Netlefi they make a yearly kind 280 00:23:17.400 --> 00:23:22.400 of review of tools that people have used and then people or i'm sorry, 281 00:23:22.519 --> 00:23:26.000 tools that they want to use in the future. In twenty twenty four and 282 00:23:26.000 --> 00:23:32.599 builder dot io is actually one of the most desired tools to use. So 283 00:23:32.799 --> 00:23:36.279 yeah, it might be it might be quite interesting to take a look at 284 00:23:36.279 --> 00:23:40.200 that. I think it kind of one. One thing I was thinking of 285 00:23:40.519 --> 00:23:44.839 as as you were talking about about Builder, I owe and the code quality 286 00:23:44.880 --> 00:23:51.319 is not so good. As I was thinking about how organizations, how you 287 00:23:52.119 --> 00:23:56.680 there there was a there's a there was a podcast from a guy if you 288 00:23:56.759 --> 00:24:03.839 know him, they call him d h as David Heinemeier Hansen. Yeah, 289 00:24:03.880 --> 00:24:07.599 it was with Tim Ferriss. And I always remember this quote. It's such 290 00:24:07.640 --> 00:24:11.880 a small, like little sentence, but I always remember this, and I 291 00:24:11.920 --> 00:24:14.559 heard this like five or ten years ago. He says, you know, 292 00:24:14.559 --> 00:24:18.960 when you build an application or even maybe even a design you make you basically 293 00:24:19.000 --> 00:24:23.720 said, software is you know, hundreds or thousands or tens of thousands, 294 00:24:25.279 --> 00:24:32.119 very small decisions in you know, different components, different style CSS files, 295 00:24:32.160 --> 00:24:36.160 whatever, in back ends, and those are done over time. Right, 296 00:24:36.200 --> 00:24:38.880 you can't, like you mentioned, so someone wants maybe hey, just build 297 00:24:38.920 --> 00:24:44.200 me a sass app. But it comes back to language and these decisions. 298 00:24:44.279 --> 00:24:48.680 You can't just say, build me a sass app because there's there's ten thousand 299 00:24:48.720 --> 00:24:52.200 decisions behind this and the AI. Okay, the AI can maybe choose all 300 00:24:52.240 --> 00:24:56.960 those for you, but then you don't know, you don't know what those 301 00:24:57.000 --> 00:25:00.160 decisions it made, and then you're stuck with this. Yeah, even if 302 00:25:00.160 --> 00:25:03.640 it could generate a giant app, you have no idea the code, all 303 00:25:03.680 --> 00:25:10.279 the code behind it, or or what it looks like. So yeah, 304 00:25:10.400 --> 00:25:15.240 for me, it's it will be quite interesting to see if those tools like 305 00:25:15.359 --> 00:25:22.519 the the I guess they I'll call for now over promising tools will really work 306 00:25:22.599 --> 00:25:26.119 because this reminds me a lot of there was a lot of hype around no 307 00:25:26.279 --> 00:25:32.079 code tools, which I think they're valuable and useful, but it I think 308 00:25:32.119 --> 00:25:37.000 you always come to a point eventually where I think, hopefully for us, 309 00:25:37.079 --> 00:25:41.240 you'll always need a developer or an engineer to to look in detail at certain 310 00:25:41.400 --> 00:25:49.000 small things and modify things like that. So but yeah, I guess one 311 00:25:49.039 --> 00:25:53.160 other thing, uh, it might be fun to talk about with with these 312 00:25:53.200 --> 00:26:00.480 AI tools is do you think do you think developers are almost getting lazy or 313 00:26:00.720 --> 00:26:07.720 or or kind of relying too much, too much on AI because I know 314 00:26:07.799 --> 00:26:11.119 I'll be guilty of that sometimes where you know, I have like a function 315 00:26:11.200 --> 00:26:15.079 idea or something, and I'll just wait for co pilot to give me some 316 00:26:15.119 --> 00:26:21.119 suggestions, right, and maybe I mean, maybe that's okay because usually I 317 00:26:21.160 --> 00:26:25.720 think you mentioned it's doing something inefficient or not the best. But at the 318 00:26:25.839 --> 00:26:30.200 very least you have, you have some generated code, you you get some 319 00:26:30.319 --> 00:26:33.079 ideas. But what do you what are you feeling about that or do you 320 00:26:33.079 --> 00:26:37.680 think do you think developers are going to get too lazy? Yeah? Okay, 321 00:26:37.799 --> 00:26:42.119 Yeah, so I think so actually because in the future, like like 322 00:26:42.200 --> 00:26:48.200 I usually say, like in the future, in the future, dependimize on 323 00:26:48.400 --> 00:26:52.599 issues. Yeah, I love develop will be lazy to do that. Now. 324 00:26:52.920 --> 00:26:56.680 That's why I usually recommend, like I usually tell like people starting out 325 00:26:56.720 --> 00:27:00.759 that don't know you see, as you're starting out, I think you're heah, 326 00:27:00.799 --> 00:27:04.880 you will actually much usefulul like developers who are actually learned to the basics 327 00:27:04.880 --> 00:27:10.559 who are kind of up there, like you're maybe you've learned so much, 328 00:27:10.559 --> 00:27:14.039 you've worked on so much projects and then you have an idea of setting things 329 00:27:14.160 --> 00:27:18.880 right at that point would just be like maybe supplemented for you an assistant, 330 00:27:18.400 --> 00:27:22.599 right, like, yeah, the air could generate the function for it. 331 00:27:22.640 --> 00:27:25.920 But it doesn't mean that if you just if you actually think it up as 332 00:27:25.960 --> 00:27:29.039 well, you just that you just want something that is faster for you to 333 00:27:29.440 --> 00:27:33.240 work quiet. Maybe you just need something you just you just need speed, 334 00:27:33.319 --> 00:27:38.079 right too For kind of engineers that are kind of more maybe senior, intermediate 335 00:27:38.160 --> 00:27:41.000 and so on, rights, it's kind of good to be helpful for them 336 00:27:41.039 --> 00:27:45.039 in the ficure to be more efficient. But for developers starting out, due 337 00:27:45.039 --> 00:27:49.480 to the way here is being kind of praised, I think the gend developers 338 00:27:49.480 --> 00:27:56.960 who are kind of getting interested into development recently may become lazy, like from 339 00:27:56.960 --> 00:28:00.200 these starts, because then, yeah, you have an issue, and and 340 00:28:00.839 --> 00:28:06.240 first of all, like I, I what actually like about stack overflow is 341 00:28:06.240 --> 00:28:10.599 the fact that it helps you to actually such and then look at all other 342 00:28:10.640 --> 00:28:14.839 people's solution, right. It gives you perspective, right because yes, judge, 343 00:28:15.680 --> 00:28:18.400 if you're right, it could you could just generate one solution for you 344 00:28:18.480 --> 00:28:19.559 and that's it. And I feel like, oh, that is just the 345 00:28:19.599 --> 00:28:25.920 solution. But then you could go to stack overflow and then read comments and 346 00:28:26.039 --> 00:28:30.160 read codes and see different solutions and you will get an idea from any of 347 00:28:30.200 --> 00:28:33.599 them as well. So I think that that's what a lot of the groupers 348 00:28:33.720 --> 00:28:40.960 will lose ultimately, that ability to be to kind of that diverse idea mindset. 349 00:28:41.039 --> 00:28:45.200 Right. So it's just it's in the future. It may just be 350 00:28:45.319 --> 00:28:48.599 like, oh, all our codes look similar because everyone is using Judge TP 351 00:28:48.839 --> 00:28:52.319 or CO pilots, Like I could just look so similar because you're just like, 352 00:28:52.799 --> 00:28:57.000 yeah, used co pilots for this, and there's no difference because yeah 353 00:28:57.200 --> 00:29:02.359 you could. I think you could look presently, you could look at some 354 00:29:02.480 --> 00:29:03.680 codes and then you'll be like, oh, this is the style of this 355 00:29:03.839 --> 00:29:08.160 person. This is the style of this person. This is how your likestor 356 00:29:08.200 --> 00:29:14.920 abybe uses it with an imperative style or something else. Right. But then 357 00:29:14.960 --> 00:29:17.920 now when you're when a lot of people become more with land on AI, 358 00:29:18.000 --> 00:29:22.160 you these styles get blood, right, you really don't know which start before 359 00:29:22.160 --> 00:29:26.720 I use it. So for the cop COOM developers really good to be good 360 00:29:26.720 --> 00:29:33.119 to make them lazy, right, because I know that disearch disearch for acknowledge, 361 00:29:33.279 --> 00:29:40.039 like getting some good mental knowledge is actually eveny important because then I usually 362 00:29:40.440 --> 00:29:42.880 usually I really use myself as an example, right, when oh, I 363 00:29:42.960 --> 00:29:48.759 just want to look for a function that does maybe something like if this sorting 364 00:29:48.920 --> 00:29:52.480 right, sort setting stuff, and then I'm trying to maybe do sorting on 365 00:29:52.519 --> 00:29:55.960 my own, and then you guctually if I, oh, jamas kid had 366 00:29:56.119 --> 00:29:59.680 is sort methought, Wow, that's so nice. I could just use that, 367 00:30:00.240 --> 00:30:03.240 and you learn about this subt method and use that. Now initially you're 368 00:30:03.240 --> 00:30:07.000 trying to just maybe use if you have an idea of that, Oh there's 369 00:30:07.000 --> 00:30:11.640 a there's a method like this, and you just want to find bad boom 370 00:30:11.680 --> 00:30:15.440 way to sort it, and then you discover duty first we're searching that you 371 00:30:15.599 --> 00:30:21.519 sw this answer a better. So that's what's usually what kind of going to 372 00:30:21.559 --> 00:30:25.960 start with our flow research does and a charge you to also those away book. 373 00:30:26.119 --> 00:30:30.279 Like I said, it limits the perspectives you use. So yeah, 374 00:30:30.519 --> 00:30:34.559 I think in the future or common future to make developers lazy kind of. 375 00:30:34.880 --> 00:30:40.319 But then it depends on the level of the developer, right, so if 376 00:30:40.319 --> 00:30:42.440 you're a senior developer, you just be more efficient, like so fast, 377 00:30:42.480 --> 00:30:47.519 because then you actually know what to do. We've had the experience you've had 378 00:30:47.559 --> 00:30:53.160 you like the foundations. Yeah, before coming thevelopers they actually the actually miss 379 00:30:53.160 --> 00:30:57.000 out on those there. So I think that's just my opinion on that. 380 00:30:59.759 --> 00:31:03.039 Yeah, I think you've brought up a really good point that, Yeah, 381 00:31:03.279 --> 00:31:07.759 I guess like before any of these tools you would just go to stack overflow 382 00:31:08.000 --> 00:31:12.079 or somewhere similar, or maybe even before that, before stack overflow, maybe 383 00:31:12.079 --> 00:31:15.880 you would even have a textbook or something like that, right, Yeah, 384 00:31:15.160 --> 00:31:19.440 or or at the worst case, somebody some program or somewhere. And I 385 00:31:19.519 --> 00:31:25.200 think that's a very important point for people starting out. And I recognize that 386 00:31:25.240 --> 00:31:29.200 in myself. You know, the meme or the joke is that you go 387 00:31:29.839 --> 00:31:33.079 you just copy paste the very first answer from stack overflow, right, which 388 00:31:33.680 --> 00:31:40.000 of course is it could work. But as at least as I've grown as 389 00:31:40.000 --> 00:31:42.799 an engineer, you realize, like you said, you read the comments, 390 00:31:42.880 --> 00:31:47.279 you see people say, well we did this, and then we you know, 391 00:31:47.319 --> 00:31:49.079 we discovered that maybe wasn't the best way, and you know, all 392 00:31:49.119 --> 00:31:56.000 these contextual hints that you can learn just as much, if not more than, 393 00:31:56.079 --> 00:32:01.039 whatever the accepted answer is. Right, And the risk I think with 394 00:32:01.200 --> 00:32:06.279 these AI tools is just input output, right. I mean, sometimes they 395 00:32:06.599 --> 00:32:09.319 will even say they'll give you like some hints saying like oh this you know 396 00:32:09.400 --> 00:32:14.240 this and this, but I'm not sure if it will. I'm not sure 397 00:32:14.240 --> 00:32:17.440 if it will be at the level where if you read like a full stack 398 00:32:17.480 --> 00:32:22.160 over stack over for post or even a blog post about something, where you 399 00:32:22.160 --> 00:32:29.000 can get all these insights and all this I guess experience, right, because 400 00:32:29.039 --> 00:32:32.960 the yeah, the job of the AI is just at least right now, 401 00:32:34.039 --> 00:32:37.880 is just I give you the best output, right. I don't give you 402 00:32:37.960 --> 00:32:42.119 context, I don't give you experience. So I think this is really tough 403 00:32:42.240 --> 00:32:47.079 for beginners, especially because you also need you need to know how to ask 404 00:32:47.400 --> 00:32:52.160 the right questions. And if you're a beginner, you don't. You can't 405 00:32:52.200 --> 00:32:55.759 even you know, you can't really explain what you want, at least at 406 00:32:55.799 --> 00:33:00.640 least very clearly. So yeah, one other thing I did, I thought 407 00:33:00.640 --> 00:33:05.880 of what you're mentioning, where maybe in the future, you know, code 408 00:33:05.960 --> 00:33:12.000 is looking similar. I I worry a bit because I in a in a 409 00:33:12.000 --> 00:33:15.559 Go code base. I've been using Copilot a lot, just because like and 410 00:33:15.640 --> 00:33:21.000 I think Go is it's very simple to write, but it can get very 411 00:33:21.759 --> 00:33:25.240 very large, and I have I have some some files are growing quite large, 412 00:33:25.359 --> 00:33:30.200 and I mean I'm doing a lot of computation, but I'm worried that 413 00:33:30.960 --> 00:33:34.359 if we always go down the path of just like yeah, just generate it. 414 00:33:34.359 --> 00:33:37.519 It works. Sure, it works, that's great, But there may 415 00:33:37.559 --> 00:33:43.160 be I think I'm worried that in the future will miss out on kind of 416 00:33:43.160 --> 00:33:49.440 what software engineering or part of software engineering is, like you know these where 417 00:33:49.480 --> 00:33:54.160 you take a task and maybe not the first iteration, but eventually you get 418 00:33:54.200 --> 00:33:59.319 to a solution. That's how do I don't explain it, not really compact, 419 00:33:59.400 --> 00:34:02.000 but perhaps like elegant, I should say. And I'm worried that if 420 00:34:02.160 --> 00:34:07.160 if, if you always have the AI in the background, just you know, 421 00:34:07.640 --> 00:34:09.920 spitting out what you need at the immediate moment, will just end up 422 00:34:10.239 --> 00:34:15.320 like with these giant projects and yeah, maybe they work, but but they're 423 00:34:15.360 --> 00:34:21.199 not I don't know, maybe they're less maintainable. That that might be something 424 00:34:21.239 --> 00:34:25.159 I'd be concerned about. Do you do you see any risks like that or 425 00:34:25.199 --> 00:34:30.119 do you have any any thoughts about that? Or maybe I'm just being too 426 00:34:30.159 --> 00:34:35.880 too negative? No, no, really, Actually you're right a point on 427 00:34:35.960 --> 00:34:39.800 that. Why to do you could get like, yeah, I usually look 428 00:34:39.840 --> 00:34:45.119 at some solutions from maybe charge you tpiano, and then I see the kind 429 00:34:45.159 --> 00:34:50.760 of boost that's what I think I mentioned that in the aspect that yeah, 430 00:34:51.000 --> 00:34:54.880 if you're trying to do something, it beats minimal on it kind of gives 431 00:34:54.920 --> 00:35:00.719 you so big and so large could down Like isn't there just like a better 432 00:35:00.760 --> 00:35:06.800 way of doing this and kind of yeah, if your experience actually maybe you've 433 00:35:06.840 --> 00:35:08.960 had the experience with that you're actually in there, Oh yes, maybe this 434 00:35:09.199 --> 00:35:14.159 is what this is. I think this should be a better way that you 435 00:35:14.159 --> 00:35:17.320 maybe modify to yourself. Right, you can just rely on the maybe all 436 00:35:17.480 --> 00:35:22.719 the code just oh yeah, this just take this works right, I find 437 00:35:22.920 --> 00:35:30.119 probably critically could you actually do some modifications right, so because of your expertise 438 00:35:30.199 --> 00:35:36.360 on your level, right, but then if if like it's not controlled right, 439 00:35:36.480 --> 00:35:39.039 the coulde bits will go very over boos. And then I said it's 440 00:35:39.039 --> 00:35:43.920 lost, like it's just like a lot of a lot of big codes, 441 00:35:43.960 --> 00:35:45.280 like a lot of like I said, was like it also is a lot 442 00:35:45.280 --> 00:35:52.000 of boss code, whereas like maybe it's just it's one weird as like a 443 00:35:52.400 --> 00:35:55.320 metal that you've probably not used in the wire or something big. And then 444 00:35:55.880 --> 00:36:00.840 when everyone looks at it, it's not if it's not it's not easy to 445 00:36:00.880 --> 00:36:04.519 read, right, So I think that's actually a very big fear, like 446 00:36:04.599 --> 00:36:09.159 because like I said, it's it's then like the consequence of yea, everybody 447 00:36:09.159 --> 00:36:13.840 could looks the same at that point, which I think I've seen it in 448 00:36:13.920 --> 00:36:17.320 most could be that a lot could be that kind of work with AI like 449 00:36:17.559 --> 00:36:22.280 that much. Could they just look simil like just try to compare. Oh 450 00:36:22.400 --> 00:36:24.920 I've seen this song, I've seen this, This looks you could even identify 451 00:36:25.000 --> 00:36:30.239 that, Oh maybe this is help from pilot or something or argy, this 452 00:36:30.360 --> 00:36:34.440 is something that it will generate, right, So yeah, I think you're 453 00:36:34.480 --> 00:36:38.559 at a point on that actually, and I'm actually here on point of that. 454 00:36:38.880 --> 00:36:43.159 So but then I trually have a question as well as we that in 455 00:36:43.239 --> 00:36:49.440 as for you, now, do you think I will actually replease developers? 456 00:36:49.480 --> 00:36:54.800 Because I know that's actually that has actually been like a very very widepread notion 457 00:36:55.159 --> 00:36:59.880 like so when people went part of it, like I literally know a lot 458 00:36:59.880 --> 00:37:04.519 of people that will want to go into cooting fully because the few they could 459 00:37:04.519 --> 00:37:07.760 be replaced in the future. What's especiality like junior developers, So what do 460 00:37:07.800 --> 00:37:14.360 you think do you think I could actually replace us all? Like, what 461 00:37:14.400 --> 00:37:17.920 do you think? Yeah, I think I think it goes back to that 462 00:37:17.920 --> 00:37:25.280 that DHH quote quote that you need to make a million decisions. I mean, 463 00:37:25.320 --> 00:37:30.039 you can argue this also for they said like lawyers and people are also 464 00:37:30.039 --> 00:37:36.400 going to lose their jobs. I don't know, because in reality now I'm 465 00:37:36.440 --> 00:37:39.960 talking like actually outside the code base, right, so your organization or your 466 00:37:40.000 --> 00:37:44.960 clients or whoever you work with, you know, whatever, these hundreds of 467 00:37:45.000 --> 00:37:50.079 emails, these these design decisions, or any part of the stack, the 468 00:37:50.159 --> 00:37:53.760 network, the back end. There's so many small little things. I mean, 469 00:37:54.679 --> 00:38:00.519 for me, the only way that AI could replace a real human developer 470 00:38:00.599 --> 00:38:07.440 is if they were somehow there and conscious. I mean then you're talking about 471 00:38:07.639 --> 00:38:10.480 you know whatever terminator anyway, So unless you can completely replace a human, 472 00:38:12.760 --> 00:38:15.960 I don't I just don't see how. I mean, they even even if 473 00:38:16.000 --> 00:38:21.159 you have the best code generator ever, it can look exactly, it could 474 00:38:21.159 --> 00:38:24.400 even mimic people on your team where you say, oh, it looks like 475 00:38:24.440 --> 00:38:29.800 that code was written by him or him. Even then it's still it's still 476 00:38:29.840 --> 00:38:35.559 only code. And I don't know, you can't replace I just don't think 477 00:38:35.559 --> 00:38:42.239 it can replace someone with experience or or yeah, you know, yeah, 478 00:38:42.280 --> 00:38:45.599 experience with multiple projects or languages and things like that. So that's that's currently 479 00:38:45.639 --> 00:38:51.199 how I am so bubbill stay maybe we have terminator in a few years. 480 00:38:50.079 --> 00:38:55.239 And yeah, I think I'll tell you I I agree with you. So 481 00:38:55.480 --> 00:39:00.159 I think from what DH from what you have reference on DH. Right, 482 00:39:00.400 --> 00:39:06.960 it's actually right, I see could like software development as they're a lot of 483 00:39:07.039 --> 00:39:10.960 moving parts. Right, so for example, you could actually have an idea 484 00:39:12.039 --> 00:39:15.519 for a product, right, and then we were working at the product you 485 00:39:15.559 --> 00:39:20.000 actually find that, oh, this business model I was feeling it's kind of 486 00:39:20.239 --> 00:39:22.639 sucks, right, kind of doesn't really work. It does work processing consumers, 487 00:39:22.679 --> 00:39:28.800 and so maybe I need to change that, right, those situations back 488 00:39:28.840 --> 00:39:34.000 and forth, you actually test and then sh whether your business model works. 489 00:39:34.159 --> 00:39:37.480 You actually gen le maybe like a formula or a concept around it. Right, 490 00:39:38.000 --> 00:39:42.760 those things are kind of I feel they're human driven, unless maybe there's 491 00:39:42.760 --> 00:39:45.159 an air like you said, that can do that, which, like I 492 00:39:45.199 --> 00:39:49.960 said, is like a amult already. So if you just just take over 493 00:39:50.000 --> 00:39:53.360 the world, then don't even participate in my standard for something that kind of 494 00:39:53.400 --> 00:39:58.440 thing, right, So so just that kind of thing. So if they're 495 00:39:58.559 --> 00:40:01.760 like unless I are kind of like that kind of level, right, So 496 00:40:02.960 --> 00:40:07.320 yeah, it's I don't think it they will actually replace you ons, right, 497 00:40:07.400 --> 00:40:14.960 because then you do those situations back and forth concepts testing, because yeah, 498 00:40:15.039 --> 00:40:20.639 I know that most most products and most such products they were not actually 499 00:40:20.679 --> 00:40:23.320 the concept of which they were created are like limeters. Like for example, 500 00:40:23.360 --> 00:40:29.360 maybe he had an idea, but it wasn't the idea that initially that came 501 00:40:29.400 --> 00:40:31.840 into life. There were a lot of changes and iterations, and then those 502 00:40:31.880 --> 00:40:36.960 changes and iterations also got reflected in coude as well, right, So you 503 00:40:37.119 --> 00:40:40.320 need someone to actually process that those changes and then put it in coude. 504 00:40:40.400 --> 00:40:44.719 I don't know if ai we could wish to that level for we right, 505 00:40:45.840 --> 00:40:50.639 changing business specification, I don't. I don't know yet. So in that 506 00:40:50.760 --> 00:40:53.719 regard, I don't think it will replace people. Now for senior developers, 507 00:40:53.719 --> 00:40:59.320 obviously, the experiences, these experiences, they're like because you can't replace song 508 00:40:59.400 --> 00:41:02.679 with against the more because they have the main experience of the whole business of 509 00:41:02.800 --> 00:41:07.800 the old thing, right, So the main experience is also very very very 510 00:41:07.960 --> 00:41:12.920 important right in the business and the product, So it's something that they can't 511 00:41:13.920 --> 00:41:19.039 really replace, right. I think most signiors will be kind of even hired 512 00:41:19.119 --> 00:41:22.760 more in their appiods. That's what I feel than than than ever, so 513 00:41:22.840 --> 00:41:28.440 they need most. Now, I think the aspect I'm having concerned with is 514 00:41:28.480 --> 00:41:30.480 with the genius. Now, I, for example, I just want to 515 00:41:30.559 --> 00:41:37.960 use an example of maybe things like like we used the website generator. Maybe 516 00:41:37.000 --> 00:41:43.039 like a ux or ux designer. Right, your job is just kind of 517 00:41:43.239 --> 00:41:47.079 design pages, right, the flow and the experience. Now, a lot 518 00:41:47.079 --> 00:41:52.280 of people have argued, and I think some people had looked at a lot 519 00:41:52.280 --> 00:41:54.519 of people who had the reasons that you were able to kind of scrib that 520 00:41:54.679 --> 00:42:00.920 division. Now it's really sorts because so many the developers that come into maybe 521 00:42:01.079 --> 00:42:05.440 things like web development, they start with the fun thing, right, and 522 00:42:05.480 --> 00:42:07.199 we they start with the fund thing. They have to stablish history and the 523 00:42:07.280 --> 00:42:10.760 design part. So this is something they have to start it. And then 524 00:42:12.039 --> 00:42:16.280 the kind of a lot of companies are kind of eliminating that starting point for 525 00:42:16.280 --> 00:42:21.559 people they can actually have the experience with, replacing them with air. So 526 00:42:21.840 --> 00:42:27.239 I think that was the aspect that was really really concerning for me. But 527 00:42:27.320 --> 00:42:30.000 then I actually then remember that, oh, yeah, there's the accessibility, 528 00:42:30.079 --> 00:42:35.320 right, because yeah, there's something about just creating the good websites and that 529 00:42:35.400 --> 00:42:38.880 have been accessible for a lot of people. So I don't know if here 530 00:42:38.960 --> 00:42:44.400 it kind of works with accessibility or maybe degenerators and so on. I think 531 00:42:44.400 --> 00:42:47.920 that one may actually be human intervened, but how many like I don't know 532 00:42:47.920 --> 00:42:54.039 how many people actually companies or so kind of a concerned about accessibility as much 533 00:42:54.079 --> 00:42:59.480 as that right, and there's certain codes they don't check for accessibility and so 534 00:42:59.519 --> 00:43:04.480 on. So yeah, so I think overall it will replaced developers kind of 535 00:43:04.519 --> 00:43:07.760 well, I think there's a rising concunt for me for people who are starting 536 00:43:07.760 --> 00:43:13.400 out, especially people are coming to each setting genio right now, now there's 537 00:43:13.400 --> 00:43:17.400 a point they were reaching the guenior that obviously I feel that he has come 538 00:43:17.519 --> 00:43:22.559 be pleasant because then at the end off they they are the ones actually implement 539 00:43:22.719 --> 00:43:25.599 those business ideas. Right, A senior has an idea, it does't main 540 00:43:25.639 --> 00:43:30.880 knowledge one idea and then it gives it to a senior who actually understand it 541 00:43:30.960 --> 00:43:35.679 and then bring up something right. And also the gueniors who subsequently become the 542 00:43:35.760 --> 00:43:39.039 seniors of the future. So it's something that we need that what is going 543 00:43:39.039 --> 00:43:43.440 to happen. So yeah, but it's for beginners who are going to setting 544 00:43:43.519 --> 00:43:47.280 domains like I know some years have actually admitted some writers, some kind of 545 00:43:47.320 --> 00:43:52.159 writers. So you see I've seen I think I've u seen the job for 546 00:43:52.400 --> 00:43:57.840 like setting on LinkedIn for AI, right, and or like what like does 547 00:43:57.880 --> 00:44:02.400 that like? Yeah? I think yeah, I tally replaced people to really 548 00:44:04.719 --> 00:44:07.679 like just some people. Right, So what do you actually think on maybe 549 00:44:09.000 --> 00:44:14.679 people like like who's or which part of web develimit do you feel that has 550 00:44:14.679 --> 00:44:20.639 been printed by maybe the sogio AI? Yeah, I think I think front 551 00:44:20.719 --> 00:44:25.840 end definitely, But even there, I I still think there's you mentioned like 552 00:44:27.239 --> 00:44:31.239 these things like accessibility. Yeah, okay, even if companies don't care so 553 00:44:31.320 --> 00:44:35.400 much about it. For me, like when I build websites, I make 554 00:44:35.440 --> 00:44:39.280 it a part to meet those requirements, right, And so maybe for people 555 00:44:39.559 --> 00:44:43.519 out there listening you might not even know this, but there's even rules about 556 00:44:43.559 --> 00:44:47.880 color contrasts to meet certain accessibility rules. And you know, maybe AI follows 557 00:44:47.880 --> 00:44:52.239 it, maybe it doesn't. But if I, at least for me right 558 00:44:52.280 --> 00:44:55.159 now, I would feel much more comfortable with a designer who knows that stuff 559 00:44:55.239 --> 00:44:59.519 like and has known it for years, right, has the experience of all 560 00:44:59.559 --> 00:45:05.559 that and and you know, color choices even I mean I've even seen I'm 561 00:45:05.679 --> 00:45:07.880 no design or expert. But I've even seen how you can look at how 562 00:45:07.960 --> 00:45:12.119 fonts are chosen, and usually they have certain reasons, like you know, 563 00:45:12.159 --> 00:45:15.320 even for uh, you know, muted text when it's a bit more gray, 564 00:45:15.519 --> 00:45:20.559 Why why you use this? And all these these things. Unfortunately I 565 00:45:20.559 --> 00:45:25.880 don't have that experience, but I can't imagine in AI just isn't designed for 566 00:45:25.920 --> 00:45:30.360 that. Again, it's it's just trained on. Sure it might be trained 567 00:45:30.400 --> 00:45:37.920 on the best websites, but it doesn't have that that contextual knowledge. So 568 00:45:37.159 --> 00:45:40.679 but yeah, I guess I think because we're probably coming towards Dana, I 569 00:45:40.719 --> 00:45:46.480 think maybe to end on on like a positive note, I think the nice 570 00:45:46.519 --> 00:45:51.760 thing. While it is hard to learn, I don't think you can learn 571 00:45:51.800 --> 00:45:55.079 domain knowledge from an AI, but I think there is hope for for the 572 00:45:55.159 --> 00:45:59.960 junior developers that it is a nice tool. For example, I start, 573 00:46:00.320 --> 00:46:02.639 I started practicing some rusts the other day. I've never written RUSS before, 574 00:46:04.039 --> 00:46:07.639 but I think it can help. It can really speed up just the initial 575 00:46:07.159 --> 00:46:10.119 like onboarding or getting a feel for the language. I mean, at the 576 00:46:10.199 --> 00:46:15.440 very least, the ais are pretty good with syntax and stuff. I think 577 00:46:15.960 --> 00:46:20.039 just for the domain and and you know, the actual project experience you still 578 00:46:20.079 --> 00:46:22.719 need to do and probably I think probably forever you'll always need to do the 579 00:46:22.719 --> 00:46:28.360 old fashioned way where you just need to have experience, you know, as 580 00:46:28.400 --> 00:46:31.239 a junior and grow into that senior role. But maybe maybe it's a tool 581 00:46:31.280 --> 00:46:35.599 to help help them them speed up. What do you what do you think? 582 00:46:36.119 --> 00:46:38.840 What do you think about that? Am I over optimistic? No? 583 00:46:39.079 --> 00:46:42.960 I think you guys one points as well. Right, So it's like I 584 00:46:43.000 --> 00:46:47.920 said, it's actually I initially stated like an assistant, right, actually fascinated. 585 00:46:49.280 --> 00:46:52.320 Right, So I think using the eyes as like a starting out, 586 00:46:52.400 --> 00:46:58.440 like starting out to actually increase your speed and lending. But then like where 587 00:46:58.519 --> 00:47:02.320 I actually don't recommend you in it is when you are actually like maybe starting 588 00:47:02.360 --> 00:47:06.960 out like on the basics basics, right, like, oh, you're coming 589 00:47:07.000 --> 00:47:10.599 down from another discipline and you have no idea what COULDE then just want to 590 00:47:10.639 --> 00:47:15.920 get into air directly, It's won't really be advisable because you're coming into a 591 00:47:15.960 --> 00:47:20.840 new discipline and then you're trying to learn something new. You actually need to 592 00:47:21.880 --> 00:47:24.519 do the work and research and find out what you need to learn. Yeah, 593 00:47:24.559 --> 00:47:29.079 But then for people like like for developers, like we have actually maybe 594 00:47:29.199 --> 00:47:32.000 worked on cettain projects and certain things that I think for us if I don't 595 00:47:32.000 --> 00:47:37.519 if you just want to learn something, I actually have the idea of maybe 596 00:47:37.760 --> 00:47:42.480 basic syntas of languages and how they are kind of similar, I could just 597 00:47:42.559 --> 00:47:45.320 use the air and like I said, just start learning something, maybe a 598 00:47:45.360 --> 00:47:51.039 new language or a new framework. Quite but then from beginners, I won't 599 00:47:51.039 --> 00:47:54.360 really advise that because you need that knowledge. You need to get that knowledge 600 00:47:54.400 --> 00:47:59.400 about it, like that the main knowledge about that new language or learning or 601 00:47:59.519 --> 00:48:02.159 so. Yeah, but then yeah, there's hope actually for the junior girl. 602 00:48:02.239 --> 00:48:06.960 Like and I think I mentioned it as well, they are always going 603 00:48:07.000 --> 00:48:08.800 to be seniors of the future. And those seniors of futures are not going 604 00:48:08.840 --> 00:48:14.239 to be the A definitely, they're going to be the senior developed. They're 605 00:48:14.280 --> 00:48:17.159 going to be the juniors a group of today. So obviously there's always going 606 00:48:17.199 --> 00:48:21.599 to be a chance for a junior to rise up to become the seniors. 607 00:48:21.679 --> 00:48:24.639 So it's something I think that I think that's that's like the biggest equipment for 608 00:48:24.679 --> 00:48:29.079 any one. Now they're actually trying to come in and they feel out their 609 00:48:29.199 --> 00:48:32.159 junior position. Yeah, so it's just for them to actually kind of work 610 00:48:32.599 --> 00:48:37.480 work on themselves and try to learn a lot of things. Right, obviously 611 00:48:37.760 --> 00:48:39.840 you're going to the juniors of today, Bill seniors of tomorrow. It's just 612 00:48:40.039 --> 00:48:45.159 it's also principle, right obviously like that. So I think that's just what 613 00:48:45.239 --> 00:48:51.960 I feel about everything about it kind of Yeah, yeah, I agree. 614 00:48:52.079 --> 00:48:57.400 I think, Yeah, lots lots to come in the future will be exciting. 615 00:48:58.760 --> 00:49:02.079 Yeah, I guess I guess with that, Ah, should we move 616 00:49:02.119 --> 00:49:09.760 on to picks or or whatever you want to support or mention? Okay, 617 00:49:09.840 --> 00:49:16.559 yeah, for picks right, I okay, for picks, right, I 618 00:49:16.599 --> 00:49:24.360 will actually recommend that build out of areos without of areas, yeah, generator 619 00:49:24.519 --> 00:49:30.840 right, So I think I'm trying to get the link figm out to react. 620 00:49:30.840 --> 00:49:35.239 Yeah. So it's something I actually want to kind of look into, 621 00:49:35.920 --> 00:49:40.000 and I definitely want a lot of people to actually look into it as well. 622 00:49:40.039 --> 00:49:45.639 I think I've kind of followed this CITU. I think it is miscal 623 00:49:45.760 --> 00:49:51.800 who is like the the creative of Angola. Yeah, so I think without 624 00:49:52.079 --> 00:49:55.320 I think they're also behind quick I think could the jerascipt framework, right, 625 00:49:55.480 --> 00:50:00.280 So yeah, I think I will past the link in the chat that I 626 00:50:00.719 --> 00:50:06.480 think more about them, So I don't know I will. Yeah, I 627 00:50:06.480 --> 00:50:12.239 think it's it's naturally on fig y. Yeah, they have a fig moth 628 00:50:12.360 --> 00:50:15.280 too. It's only easy fig moth too actually, and I think they'll be 629 00:50:15.320 --> 00:50:21.360 linked to the always set on how to do it. So yeah, so 630 00:50:21.480 --> 00:50:24.639 I think that's just my topic for today. And then yeah, so what 631 00:50:24.880 --> 00:50:30.880 what's yours. I'll also take the builder I owe as as a homework. 632 00:50:30.920 --> 00:50:34.760 But yeah, I just wanted to mention. I think it's finally time I 633 00:50:34.840 --> 00:50:39.360 might destroy my email inbox. But so, I have courses on my blog. 634 00:50:39.800 --> 00:50:44.519 I call them full stack courses, and I've mentioned in previous episodes, 635 00:50:44.559 --> 00:50:49.639 so I try and focus on it's either like a very specific kind of niche 636 00:50:49.679 --> 00:50:53.800 thing but that's usually very helpful in multiple applications, or it's more of a 637 00:50:53.920 --> 00:50:58.159 kind of you know, not a full complete sas at, but but some 638 00:50:58.199 --> 00:51:04.519 sort of working functional app that you build. And I will mention for people 639 00:51:04.559 --> 00:51:10.679 who for any reason can't can't afford the course that I do offer them for 640 00:51:10.719 --> 00:51:15.760 more or less for free. You can even so the first few lessons or 641 00:51:15.840 --> 00:51:19.719 up to almost half of the course, they're free on YouTube. This is 642 00:51:19.719 --> 00:51:23.400 all from my blog. I'll post the link. But then, yeah, 643 00:51:23.400 --> 00:51:27.599 if you can't get the full course for any reason, just just reach out 644 00:51:27.599 --> 00:51:30.920 to me. And that comes with an honor system. So you know, 645 00:51:30.960 --> 00:51:35.639 if you're a dev and you've got a job, I would like if you 646 00:51:36.159 --> 00:51:38.559 pay for my course and support you know, what I'm building so that I 647 00:51:38.559 --> 00:51:44.199 can make more of these in the future and help more developers. So, 648 00:51:44.320 --> 00:51:46.639 but if you can't just reach out to me, I'll get you the full 649 00:51:46.719 --> 00:51:53.360 course one way or another. Yeah, that's that's all from my side. 650 00:51:53.679 --> 00:52:00.840 Yeah, that's also so I think there is I mean, not much content 651 00:52:00.880 --> 00:52:04.440 to this, so yeah, I think we are. We've come to the 652 00:52:04.559 --> 00:52:08.440 end of the podcast today, right, so all right, and I think 653 00:52:08.480 --> 00:52:14.079 maybe I could just leave some partying words for the genior developers, like just 654 00:52:14.199 --> 00:52:17.760 keep on keep on, like keep on learning, and don't be afraid of 655 00:52:17.800 --> 00:52:22.960 AI, because, like I said, yeah, it's artificial intelligence, but 656 00:52:22.320 --> 00:52:28.800 they're actually like they're like the real intelligence, the human intelligence. They're the 657 00:52:28.880 --> 00:52:30.719 original no matter what, and you can't do this place