From AI Hype to AI Harness Engineering – Building AI That People Can Actually Trust with Alan Buscaglia [MVP] from Gentleman Programming

Vihtoinkin! Aika tehdä kesämuistoja, tullenna kesän parhaat hetketkuvatua teisiin helosti. Tila ennen yhdeksestä toista heinekuuta ja saat ilmaisen toimituksen yli-kymmännen euron ostoksille. Ivorourpistefi! Suuret päätökset voivat pienekauas. Siksi tarvitsein rinnaleeni kumpanin, joka ymmärtää minne ollen menossa. Ja, hii, minun jälkeen. Nyt on mukava, että on mukava. Ja jos on mukava, Today, we are diving into one of the most misunderstand areas - of artificial intelligence. Everyone is talking about AI, everyone is building AI - but very few people are talking about how - to engineer AI system that are reliable, manageable and - actually useful. Today's guest is someone who lives exactly that section. And Buscargili is. Yeah, he's a difficult last name. No word. The name is Alan Buscargili. It's difficult. No, it's not. Buscargili. Yeah, it's an app that is - a prologue, Microsoft MVP, Google Developer Expert - in Angular, EduKTRA, Open Source Contributor - and creator of massive Spanish-speaking tech community - Gentleman programming. -Exactly. -Reaching well over 200,000 developers - across YouTube, Twitch, Instagram, Discord, GitHub. Yeah, maybe we were man, maybe we were. Yeah, I predicted. Yeah, it's quite focused on something - in critical exciting, loop engineering - and AI hours engineering, the discipline of creating - AI system that constantly delivers high quality outcomes - instead of unpredictable magic tricks. We are also going to discuss community building, - developer education, contact creation, leadership - Microsoft AI ecosystem and what the future of software - engineering looks like in AI first. So welcome, and then to the M365 show. Yeah, thank you, man, for the mutation. It's a mess in the cell. I had to go to this. It's a perfect thank you for that. Yeah, I think there are a lot of people - low you but for people meeting you the first time. Who is Alan? Oh, Alan is strange. I'm a workaholic. But more than anything, I'm a teacher. I consider myself a teacher. I love teaching and love sharing knowledge. I think knowledge has to be free and it has to be everywhere. So that's why I started my YouTube channel - that is "Gentieman Programming", you can also find - well, as you say, everywhere. I perform that. I'm also a perform content creator. I'm also an open source developer. I create in AI tools like Gentlyi or Engram. They try to simplify people's lives. Not only people are developers, but I have people, for example. There are COs or working on data science or - even finance. And they use my tools and they say, "Hey, this is not anything." So perfect. Yeah. And you did become both a Microsoft MVP - and a Google developer expert. Exactly. Exactly. I put in more walls. Yeah, it's really amazing. So I think it's the. Yeah. Three big, I think Amazon, Google and Microsoft - I think it's three bigs that you have more to four to four of them. So you have to collect all the other stuff. Yeah, yeah, yeah. Amazon, you know what to do now. Yeah, when you look back in your career, what. Yeah, decision change, everything. Oh, a lot of stuff. But the principal thing, and no worries about this, I'm. You're going to find that I'm super open about everything, okay? And through and through. Transparent. Okay, in this case, the thing that make a click, in my case, was my father's death. Okay, it was like something that really made a click on me. It was one of those people that are just, I don't know, lazy. And when that happened, everything came true. I had to be like the men in the house, you know? And they cared of things. And yeah, that really made a change on me. I started having, I don't know, grabbing a university more serious, studies, my career, also, everything, everything. And when I start working, I do have a mentor. I do have a tutor, right? For everything that's a program related and such. So I try to be that one, for people. But that's why I'm creating content. I try to be that mentor that I do have. Yeah, I. Yeah, your concert experience is really interesting. You have the gentleman programming. And I have tried to validate it on some tools. But it's all says it's one of the largest Spanish-speaking developer community. How did all this begin? Well, in pandemic. You know, in pandemic, you could have two things. Or you have a kid who starts creating content. So in this case, they're creating content. The kid came after. So, I don't know. As I was trying to get myself, you know, something, trying to do something. I always love creating content. I use to, for example, to create content for my companies that I work at the time. I also started communities in those companies. So I say, okay, let's merge those things up. And boom, the gentleman programming came through. That was the main thing. Yeah. And have you. I think on YouTube, you have more than 120,000 followers. Oh, yeah. I think it's a right word. Have you ever expected to reach this? Or was this a plan? No. No, not at all. Not at all. I still remember when I had my first thousand. That it was almost crying. It was crazy. Because I was thinking, okay, first. Why? Why people are watching me. What I had to offer to these people. And having people tell me, you know, I had a job because of you. Or you have me in this and the other. I came through this difficult challenge because of when you're teaching. Because I don't only teach programming. And now AI. I also teach software skills. So, soft skills. I teach. I know one of those guys they have like a phrase for everything. You know? So, I know. I like giving advices. So, for example, I used to have a space in my streams. Because I also do a stream on Fridays. And I had a space that was one-on-one. Where you can just get into this corner with me. Talk about something. Ask me something. And I was going to try to help you. And the number of people that came in. I just have to say thank you. You know? For those kind of stuff, thank you. It was amazing. And I still don't get the numbers. I want to live from this. I don't even want to leave my coding job. Because I love my job. I love working. You know, because when you get into my case, right? I'm able to open source. That's amazing. Open source security company. I'm still learning. And I'm hands in the challenge. And if I get out of there here, what do you have to teach people? I don't know. Teories? No. I like teaching practice. So, it's a little bit of everything. It's amazing. What people gives me, the satisfaction of that kind of feedback is just. It pays for everything. Yeah. I think then is one, one, what the people say. And the feedback from the people was one thing that motivates you to continue screening the educational content you did. But I think at the start, it's, I feel the same. I have, I don't know, on 100 follow-up on YouTube and do every day. It's really hard. How did you motivate at the start? Yeah. I don't know. I don't really know. I think it's just one of those things that, you know, gets to you. I don't know. I used to help a lot of people in the university, you know, and even school. You know, those guys that always give a hand when there's an exam, you know. ja peso savu tie, in the last minute. But the issue is that the people that I teach, they pass the exam and not me. That's a crazy body. But I know it's something that is just like a call. I don't know. I really love doing this. That's the experience. And I think you do so much in all this channel and you have a drop. You do speaking. You come to podcast. I think you have also a family life and you do the content creating. How did you balance this? This is awesome. It's difficult. It's difficult. It's a lot of time because I also have a family. I also have a kid of two years. So I had to balance everything. Because as you say for me, my job is my life. That's the thing. I work eight to nine hours in my, let's say, official job. I have my own business. But then I have my integration. I have the open source and have everything. For example, now I'm a vacations, but I didn't sleep at all. I have been doing open source. It's like crazy. And I love it. I love it. It's one of those things. I know people like watching movie when they're vacation. So going somewhere. I love working. I don't have any pressure on my things. So yeah, it's like that. We have my phone with me. I connect remotely to my computer. I give an instruction and continue my life. And just manage things. That's awesome. You have a kid who you're also saying it should also become a thought leader or I think in this generation it's more influencer. and boom, I merged it if it passes. That flow is a harness. Exactly that is a harness, right? You say first, whenever you have implemented, you have to see how the code is made, what are the conventions of the project, then how is the template of the commit? That you have to use to do the commit. What is the template of the PR? That you have to use to create the PR. All the continuous integrations, tools, or reactions are green. Are they working perfectly? Now you can merge it. Those are harnesses. There has been here for a lot of years, and now we are expanding them into A.I. Yeah, I have the last week. I read a funny study, and that is from how, in which language you ask the same questions in Cloud Code, it gives different answers, and it is trying to be more like the stereo tip, like if I ask a German, it is more straight. I don't know, in other language. Yeah, that is really funny. So, did you think that the IARLIS is something why a lot of A.I. Many A.I. projects fail. Yeah, I truly would do so. What's most I think mine can fail at any time, because something that you do for one model, is not only the model, the F4, okay, for that model, may change the response, right, the output. So, every single time that something happens, in my case, I have my great community, there's always time to test and stuff, right? So, it's like, okay, this works amazingly on, let's say, a GBD 5.5, but now that 5.6 is here, it's not working correctly. Okay, let's see why. And no, because it thinks too much, okay, so I had to change the harness. Or maybe the harness did not need it anymore, because the model is training in a certain way, and it just works, right? So, those are the things. It's difficult. It's really difficult, really difficult. And when you create a CLI, or I say a CLI, because I know, I think it's a clock hole. The clock hole is a CLI to execute the Asian, right? With all the prompting and the such. I don't know, I think that most tools fail because they are, yeah, they try to over-engineer the solution, the harness. And when you over-engineer the harness, a lot of things happen. First, when you harness something, you give context. And when you give context, you are getting the context from the Asian. Okay, so you're reducing the amount of context window that the Asian can use. And even you're using motorkins for that. So when you over-engineer, these kind of things happen. And let's say it, yeah, I imagine TNM. Okay, so in Latin America, we had to say it, having to spend a lot of money in forced descriptions on the eye is difficult, right? It's really difficult. So that's why a lot of people use, for example, it's a open code, and they use one subscription of code code, X, Copilot, whatever. You have it as a main base. And then they use open source models for everything else because they're cheap. Right? So that's the thing. When you over-engineer, you're also affecting this people. They're trying to get into the eye, but don't have the resources to spend a lot of money to have it, let's say, cut, right? So it's super difficult, right? So that's, I think a lot of companies and people start with the small language models, actually, start building their own or try it. So, yeah, I think that it's, yeah, yeah. Yeah, it's them. The glau trunks are so damn expensive. But how do you make a eye outputs reliable? That's the thing. It's difficult. Really difficult. What's more, while we're talking, while we're talking, I have one, two, three, four, six sessions doing things for me, right? And what they are doing is testing, like crazy, all the harnesses that are implementing. The thing is the following, you have to have a complete set of end-to-end tests, is like 100% and needed. And apart from that, you have to have a certain way of benchmarking it. Okay. You have to bench it. So are you spending more tokens? No. Okay. But how much time did you need to reach the output? Less. Okay. That's perfect. Less tokens. Less time. But what happens if you start doing things like, something that I'm doing, okay, spoiler? I'm trying to use algorithms to reduce the amount of tokens that are used. So, some of the computation is on the CPU instead of an affination. Okay. You're using less tokens and maybe the algorithms are a little bit too much and you're spending more time. And that's the better per experience issue. And whenever you say, okay, use this and it's going to use a lot of less tokens. Perfect. But if you have to have, I don't know, spend three hours of your life to change one line, wearing bad terms, right? So it's a balance. Everything is a balance. You have to see how fast you response, how much it costs. And again, how the term, how the term, you can make that output. And that's one of the most difficult things also. Because it depends again on the model of the effort that you use. It's super difficult, super difficult. So you do a lot of testing and spend a lot of talking. I don't want your, uh, both your cloud cars are what you use. One of the most difficult things to do is to get the money. The customer doesn't have to pay for the money. You can't buy a lot of money, but you can pay for the money. You can buy a lot of money in the money, and you can buy a lot of money. You can pay for the money, but you can't pay for the money. 50,000 and you can't pay for the money. Shannen Maldonado is a famous artist who has been working for the whole year. He was a shopkeeper because he was a salesman in the company who helped the company to get the money. He was the first to pay the money and the company we were working for. Can you a little bit explain how a feedback loop looks when you're working and do you is it in human feedback loop or is it also doing feedback loops with AI? In my case, I try to be over everything. Okay, I don't like just say, okay, do this. Perfect. Merch it. Now, that's not me. I try to be the human in the loop. I try to be the overseer, let's say, of everything. So in my case, what I'm doing? For example, I can give you an example of what I'm doing right now with all these sessions. So I have an issue in Github, opened by one of the people from the community because they are testing my latest version and they can see an issue. Just perfect. I love them. I love them. As they are also using a Gentelei, the issue is really reductive. Okay, it's really detailed. So I grab the issue. I go into one of my actions. I say, okay, perfect. Let's see what happens. Okay, give me a detail of what, whatever is happening right now. So it goes into the code, it reads everything and gives me a feedback. This is what's happened. Okay, perfect. Give me some possibilities of some solutions. I'm going to also give you my take of how we can resolve this. Put everything into place and let's see what's the best offer. Give me advantages, disadvantages and the such. Boom. Give me all the possibilities and a select one. Perfect. From there, it depends. If it's a really big issue, I try to do something like SDD, expect during development. If not, I try to just go with it. Okay, give me an app proposal and see the design, the solution. It starts working and I always try to limit the scope of the work. So let's say that we have a big issue that has a lot of steps to resolve the issue. Perfect. Let's try to stop at every single step and see what happens. What's, how is going? What's the, at the output? It's performing as we want to also. And again, are we using TDD? That's during development because that's super important for me. Yes, I'm using perfect. All the end to end test are passing. All the end to end are related to the behaviors that the people in the issue are describing. That's a really good gallery. Also, a really good harness. Use TDD, that's the greatest harness for me. So again, it's like that. I'm always part of it. And everything that I just told you is automated in Jettelay. Every single part of it because that's my way of working. I try to create my own look that is this, this way of working. And because I always do the same thing, that's why I created this flow, right? That Asian has to follow to give me an assolution. And when we think about people, what teams they will start with, elevate AI quality, what tips can you give them? Okay. First, don't trust AI too much. That's the thing, right? Because you're going to see these people, like for example, the greater of open cloth, you're going to see that he has 20 monitors, right? With 100 Asians running everywhere. And they'll say, they are watching a picture of him. So these are the amount of Asians that I can run on my Mac Mini. I had like 27 Asians running. First, that's amazing. And I trust me, he has a lot of gates and position to stop all the Asian. He has spent so many hours configuring all the setup, you know, all his loops and even for this to work. That's the first thing. Second, again, you have to test things on your own. You have to check things out. You have to also talk with your peers. Okay. How do we resolve this issue? This is the way that the team has to work to resolve this issue. This is a team convention. Perfect. I'm asking this because that's exactly what the AI has to use. Okay. So when you are working on a team and the team, even the team doesn't know how to work, the AI is going to make the famous AI slop. Because maybe it's not slop. It's the best code in the world. But the issue is that it's not the best code for your current context. And that is the problem. How the AI is going to understand how your team works or how your project behaves if you don't give it to him. That's why you have to cap the correct set of skills, right? And every single time that you are working on something and you see that the AI is making these mistakes, why don't you just create a skill for it not doing it again? Right? Whenever this happens, this is the way you have to behave. Perfect. And share with your team. Let the team know how to behave. So it's always been the overseer of everything being there. Awesome. But I think a few years ago, the front engineering was the goal of mind of people there. I don't know. Very the company's part five, 100,000 euro for doing this. So I think now we are in a new era with, yeah, agent systems and so on. Did you think the new gold mine becomes the, I don't know, I call it AI Audita? Yeah. Does it think, right? I mean, if I ask everyone right now, but every single person in the world, you see the AI as a developer and I tell them, tell me the problem you just use. And more than sure, the prompt is 20 words. So did like that because right now the prompt engineering for me, and this is going to be a debate for me, prompt engineering is there for real for me. Pro engineering is there. I don't have to engineer a prompt. Whenever, for example, if I had to review an issue, I suggest a explain. I just say, read this issue. Boom. That's it. I don't have to give him a super propose with every single step because that's what the skill is for. That's why you use a loop. You create your engineer, your loop or your harnesses because you don't have to spend time doing a prompt. All the hour has to be inside how the Asian has to behave. So when you give it a prompt, even if it's super simple, it's going to be like you want. Right? For example, what was the issue before that the skills or the agents and the and such were not the best or they were not available. So when you have to prompt something, you have to give all the specifications and all your needs and all the behavior that we're talking about previously and the such. But right now, it doesn't care. It doesn't really care. You can do whatever you want as you have put some time previously. Right? You think about what you thought about how to use it. And from there, it's just going to be here, whatever you want. You're not going to spend time doing prompts. You're going to spend time thinking that that's what we want right now. And that is another issue. What do you feel? What do you think about it right now? And I say, okay, I'm excited, but I'll also tire. Because right now is what I always wanted. I was always someone with another thoughts, a lot of ideas, a lot of I want to do this, but I don't have time. Right? And now is I have all the power in the world to do it. I can do whatever I want, but the thing is that I'm doing a lot of things at the same time. And that's tiresome, really tiresome. Even when you're working, for example, not only my things, right? But when I'm working on my company, I'm a problem. I'm working at 20 things at the same time. Okay, I created these reports at the same time going to review this PR or the same time and going to do everything. Right? It takes a toll, right? In your brain and how things are working there is difficult. So whenever you see that people say, okay, I'm going to use AI, so I have more time for myself. That's not the output. You have more time to do more things. That's the thing. There was an explanation of the CEO of Gloubant, that is a really big company. That's more. It started in Argentina, in my city, more de plata, and explain, okay, previously you have a client, okay, and you have this amount of work. And now for doing that, you have less amount of time. So what do you do with the other quantity of time? You do more jobs. That's the thing. You create more work. And it's really difficult and that's the market right now. Even if you create a company, that is a software factory, you have to produce a lot more to reach exactly the same benefit as before. Because other companies are doing the same thing. Are you a company? be thinking on how I can have a bigger output with less cost. But I think it's that there's a human cost in here. Right. So it is difficult. It is a really interesting challenge, we could say. Yeah. I think you are called a higher harness engineer become as common as deaf alps. I think it's true. Yeah. It's true. What's more, what's more, Github has a release, a new function where you can just use natural language to set up everything for your project, for the, from the continuous integration, the working actions, everything. You can just use natural language for that. And behind it, you have an age to do everything. So yeah, I think I think it's going to happen like that. Yeah. And for people that they will look more deep dive in an airless engineering, are there frameworks, learning material or tools for them? Okay, that's difficult. Why? Because right now, and trying to be 100% honest, 100% honest, I would say that I create a video right now, okay, and explain harness engineering, a loop engineering, and everything. In one week is going to be updated in one week. And for example, do you remember Ralph loop, the theme of wrong fluke, that is where it was named after a character of the Simpsons. Well, yeah, exactly. It was difficult to remember that, right? But it's not, it has not happened a long time ago for real. But it's such a thing that it's just the time pass, right? There are new things. So whenever you see, no, because you have to use Ralph loop, no one use it anymore. No one. It was more codex. It was trying to have what it has a functionality that is a slash goal. It's a rough loop. It tries to get you into the solution iterating like crazy and expanding tokens like crazy, okay? And people are 50% using it, not a lot of developers are using it. So it's the same thing. What do I teach about Ralph loop or the basics of everything? That's why you have to see. So in my case, I have a book where I am doing all the teachings. It is the amazing book, "Gentema Brahmin". That's it. If you search in Google, it's going to appear. It's free, open source, and online, okay? You can even download the PDF from there. And I have a lot of content on this subject. Apart from that, I really, really, really try to explain people to lend the basics. They'll go directly to AI, try to learn about patterns, about architecture, for example, clear architecture, external architecture, those kinds of stuff. And even some, let's say, XP development or the Scram know because I hit Scram, but this kind of soft skills, right? Kind of titles. Because right now, we are doing a Scram of Asians. 100%. We're doing a Scram of Asians. We're trying to get Asians to work like humans. And that is the orchestration that currently we have. Like, for example, right now, there's a concept that is called orchestrator minion, right? That have been used for a month until they have the name. That's the other thing. Now it has names, everything is a V name. So in this aspect, you have an orchestrator that is the one which you talk to. It learns what you do you want and orchestrate sub Asians to work and do all the intrinsic ways, let's say, of details of the implementation. They report to the orchestrator and the orchestrator talks to you. Okay, this is what they have done. Okay. So this is nothing, nothing of their difference of what, I don't know, a construction company does, right? You have the orchestrator that manages the workers and is going to tell them, okay, here, you have to create this wall, here, you have to graze this floor. Perfect. You have to do this way, this way, this way, perfect. Report to me when they're done. And when everything is done, it reports to me. So, for example, let's say the orchestrator finds that there's an issue. If it's a blocker, let's say, I don't know, I don't, we don't have more concrete to continue working. Okay, that's an issue. Okay, that's an issue that I want. But okay, one of the workers did the wall, but it did on the floor. So that's an issue. Yes, exactly. I'll go fix it. What do you want for me? Okay, that's the thing. So it's exactly the same thing. It doesn't change, it doesn't change. It helps people relate. But we are trying to get that into Asians. So if you learn about soft skills, it's going to be super beneficial for you. I'm telling you. So if you want to learn from this, read X, yeah, the platform for Elon Musk, go and read X, go and be there, follow people from the industry. There are 100% all the time talking about new things, thinking, ways of working. And you're going to learn a lot. It's the best way of doing it. Yeah. You are the first guy in the show who say X or other things. No, yeah, I prefer X, I prefer X, for example, I really, really like DAX, DAX is the creator of Open Code. Okay, you're going to see here, sorry, in the platform, he's a ball guy with a beer and he is amazing. Whatever you read from him is amazing. And I'm learning a lot from him. A lot. Whenever he has a wheel working, I say the other day, he has been a really big fight over X of, do you read your code? It's super simple. Okay, and the creator of Gosty just put this phrase, I read my code. That's it. There was a big discussion, people bashing to each other, fighting about that comment. Okay, you have to read your code. You don't have to read your code. You have to read the output and the such. So it's amazing to see different ways of thinking about the same problem and what are they response into it, right? So it's great. Super great. Yeah, awesome. Yeah, I have to, I was long, long time, it was, I was long time not not on X because it was sometimes I feel it was a little bit. I only see other musk every, every pull. I don't know. Now I see what you say. Yeah. So yeah, but I hope they have and they have better algorithm. I have to check it out or I follow the wrong people. So I have to check this very good. Awesome. My bias. Yeah. When we look at all, all, all, all these amazing AI tools and I don't know so many pop up and the companies invest so heavy in, in, in, in, in, yeah, they make, uh, and video people not to get the cheapest guys in the world. So, um, how did you see the investment in AI and will you think there is one company that's yeah, that's will win the race. Oh, I don't know. I don't know. It's really difficult because the company did, I don't like is the one that is making the biggest, let's say, influence or yeah, it has the advantage on companies, on companies, but it's losing developers. The thing is, okay, I'm gonna say, I'm saying it publicly, I think for example, this is a ontropic and tropic is winning the company race, the company race that companies, you know, they pay for tool for the people and the such, and they're winning that aspect because it's doing what Google does. Google, it's everywhere, right? If you open Google Drive, if you open Gmail, what do you find Gemini? You have Gemini everywhere. And then you can't work without Gemini and the same thing with Copilot, with Copilot, if you use, um, Microsoft tools, you're gonna see that you have Copilot everywhere and Chloe is doing the same thing now. Okay. And tropic is doing the same thing. You have clothe, work, clothe, um, workspace, it is or cowork, I don't remember, they go work. Well, where you can work, sorry, you can make clothe work your computer for whatever you need and you can share that with another person. You can share it with a peer. So, for example, you're in a marketing team and you are working on a way of delivering a response to a client as soon as possible with certain complexities. And you can share that workload. I say, this is the way of having working with this. And you can share it. You can work in it. It's great also for creating documentation. I don't know. Those kind of stuff is amazing. But on the developer side. I don't know. I think the most are really expensive. For example, again, I'm a Latin American. So when I see that you try to charge $20 for or 20 euros, in my case, for a tool for just two problems. It's crazy. Okay. The $20 subscription. It doesn't do anything. It's just two or three problems and you're down. That's it. And. And for example, GPD. That I really like the models are really the models are really like also how cheap it is for me for me is really cheap. It has almost the same performance in if not better because if I for me it follows better instructions and for the $20 you can do a lot. You can do that. Or even if you go into open search territory. Yeah, you're not going to see that when or I don't know or. I don't know. But company wise is always the same three is Google. Antropic and open. They are the ones for the glory going to for the glory. Yeah, I think in enterprise there's a Microsoft have had has this enterprise company so they had a really good starting point with the with the start with the baddest product, I think. From my perspective, but yeah. But yeah, also in the large large language models are interesting. Not yet. I have been reading about it. I have not seen it. And I think that the mask are mixing now with coarser the own course I think and they are implemented these new models this flagship new models with groc. And they are reaching fabled. Let's say reasoning, but at the fraction of the cost. So again, it's the fraction of the cost that the import is important for me. So I think a lot of companies are going to the same going to release more models. They're going to release, you know, drain to bowl. But I think that right now the reason is not the issue, but the resource consumption. That's the thing that everyone has to be working on. Yeah, I see a lot of people say, well, I, I, I don't know, the best images is this, the best video is. Yeah, yeah. For coding as this for I don't know writing emails is this. I see a lot of people starting running on their own systems because they don't need for everything these big models. So I think that it's going to also be something that we are getting in this time a little bit back from from the cloud era back to the classical PC. Yeah, yeah, by the cost of yeah, let's it's them hard. Yeah, let me do something really quick right now. I'm going to have a tool that is from the greater often open claw that is called codex bar everyone install it is amazing. And the here I can see my weekly and my five hours limits. How many research do I have because open high is giving them a research like crazy. And I can also see how much. I will have to pay if I was in a subscription. And that's crazy because right now with the amount of work that I have been doing with a $100 subscription. Well, I have the $100 subscription. I will spend more than $600. So yeah, the motorway is crazy. And for example, with a quarter of the work. 500 for an topic and again, having been using it at all. So yeah. Crazy. Yeah, today I see a guy that has developed for the Mac mini and in this play you can add it on that shows you the cost. Yeah, you're actually running. So yeah, yeah, cool, cool, cool, cool gadget. But what did you think will will be the future of the developer. How do do do's look this will will I I don't know. Yeah, make this just jump in the future. I don't know less than important or more important or. I think it's going to be just like a keyboard for real. But for me, for example, when you think about coding. You're of course you think about code, but how do you make that code. With a keyboard, right? The keyboard is the the tool for an end. Yeah, it's going to be exactly the same thing. I have a coworker. He doesn't use a keyboard. He just speaks to it. And it's funny because you are talking with him. And you say, okay, yeah, we have to fix it. Yeah, yeah, let me try to search something. And from nowhere, he meets himself. And you see him moving his hips. And then he am used to say, yeah, this is what's happening. Okay, what have you done right now? No, I was picking with claw. Okay, thank you. Go for it. You know, it's crazy. It's crazy. People are leaving things that we have used for a lot of years. For the new stuff and things are going to happen. But the main change has to be that people at least, at least has to stop being coders. They have to start being programmers. For me, programming is not coding. And then coding is a part of programming. Yes, but it's not the main thing. The ideas, the concepts. The issues and their solutions that are what programmers really aim for. What to do for a certain challenge. Okay, what are the best possible outcome that I can create with this requirements? These are the things that are going to differentiate really good developers. And you know, people are just there. I work at a colleague. Yeah, what I found really interesting. I do every year. Yeah. Look at the link in graph. The knowledge graph. And you see how different jobs are changing. What skills are companies searching for? And you see, especially in the development and architecture, IT part, it's soft skills are really come so important. I think it starts with for 10 years. It was the obligatory teamwork. And then hard skills, hard skills, hard skills. Now we have a lot of soft skills. And we have a lot of companies searching for. That's really, really interesting. Not only. Yeah. Yeah, you also teach soft skills. How can people learn or adopt soft skills in their work? Okay. I have one way of thinking that is super simple. It makes the basics of what soft skills really are. Being a good person. Yeah. Let's try to summarize some of the soft skills that companies want. They want someone to know how to teach. Perfect. Being a good person. You want someone to that learns fast. Okay. You have to learn how to ask. Right. So you have to have that requirement. Again, if you ask nicely, being a good person, then you have to understand your challenges. And you have to share it with the team. Again, it's always trying to be a good person. What do I have to do to have a great set of skills? Think about what is the correct way of aiming for this target that is having an outcome. For example, the main issue that is happening right now in all components is communication. Communication is really difficult right now, even in small companies. Having people from the team communicated with other people, they are remotely working about a subject is really difficult. I just want going to say something that happened to me when I was, because I also teach companies how to use AI correctly. There's a phrase that is stuck in my head that is, no, I don't ask my peers any kind of questions. So how do you know what the issue is? Even if you have the name of the person that made the issue, why don't you ask it? Because I just use the AI for that. I ask the AI, "Read the code and tell me what this person did." That's it. No, that's not what you have to do. You have to ask the person, you have to relate to him, you have to share. Again, if you stop sharing, the AI elucinates, it makes you elucinate. You have to talk with your peers, you have to talk with your team, you have to talk with Prouddod. You have to be part of things. You can't just be a mediator, right? The person in the middle, that's perfect, you also have to be on front of it. You have to lead what you want. So again, the soft skills are one of the most beneficial set of skills that you can have for real. Yeah, so I have an every a certain, a quick fire route. I asked some questions and you say, "Short answer, what come in your mind?" What was the coolest project you ever built? Oh, Gentile, yeah, yeah, yeah. What doesn't let me sleep for real in the evenings. What is MemoOne technology company says? You get all the money and resources you need. What tool will you build? I will try to make something. Well, maybe this is a strange, but I will continue doing what I want. I mean, doing what I'm doing, okay? Really are your own tools, but I would like to have people working with me on it. Because right now is really difficult doing open sourcing. I know if you have seen already about open sourcing death because everything is being made with AI. And you have a lot of AI slop. If you got a really good community, it's not a slop. It's ideas that are being shared. That's what you have to see, right? But it's really difficult for me to say, okay, this person is great. I trust this person. I'm going to make him a maintainer. It's really difficult because they also have to have time and they have to share your, let's say, your point of view of what you want, right? And let's be honest, that's a job. 100% a job. And you can expect being so, let's say into the project as you. Okay, I created it. Of course, I go into spend a lot of time on it because I love it. It's part of me, my baby, but I can't expect the same for someone else. So if I have all the money of the world, I will have people join me to work on this project. I'm trying to increase it to amounts and no one expects. Coffee tea or energy drinks during the about month. Coffee, coffee, coffee, 100%. Yes. Mac Vanlos Alinux. And Linux. Rocker's Accubanators. Grownies. YouTube or Twitch. YouTube. MVP or GDE. Oh, difficult. In the middle. In the middle. Because I like things from one and from the others. Things are this like between them. It's difficult. For real, for this one, it's a point in the middle. Angola or React? Angola for now. Barcelona or Silicon Valley? Barcelona. Boxer podcast. Box. And then, what's the difference between the two? One sentence that describes the future of AI. Let's see. Okay, this is one that is with a lot of effort. Okay, I hope. I'm trust. I believe human in the loop. If that happens, I'm. Wow. I'm golden. But it's not going to happen. I'm going to be my preference for this. Yeah. What's the next for gentlemen programming? I would love for you to be something great. Like the harm in your mother. It will be legend. Very. Yeah, I always end up every episode with the same question. I don't know. It's going to Tommy Jagger with a lot of things. A lot of options. And it's like it's super in gelatin. And your nothing is totally opposite. You know your things. You know the context. You know what you have to do. How to do it. Use a tool. Okay. It's not your boss. It's a tool. An assistant. If you want. Yeah. Yeah. Yeah. So I'll thank you for for joining me today. This has been incredible conversation. Not just about AI. About about engineering community building leadership. And the building technology that helps people instead of simply chasing the latest trends. So yeah, thank you for for staying with me. It's was amazing. Thank you. Thank you. Thank you so much, Mikko. I really hope that everyone liked this episode. And see you in the next one.