Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

Code & Curiosity by Maximilian Schwarzmüller

Code & Curiosity by Maximilian Schwarzmüller artwork

AI's an amazing enabler for devs

Dec 5, 20258 minAudio
  • Apple Podcasts

AI is not just a great assistant or for "vibe coding". It's also amazing if you know stuff but not everything.

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Transcript

From the show. Tap a time to play from there.

When talking about AI from a developer's perspective, I think there's one aspect that's a bit Because of course, AI has a big impact and of course, you can look at AI and dismiss it and say it's, uh, all garbage, it produces horrible, uh, results. You could say it will replace developers and we'll all vibe code our apps in the future. Or you could have a more nuanced take and say what I believe, "AI is, is a great

assistant, a great tool that can make you productive, more things done if..." And that's the important part, "If you have some experience as a developer, if you can combine your knowledge with AI." And I've said that in many v- videos and episodes and I don't wanna repeat all of that here, but there's one thing that's missing maybe or one thing that I also find important when we look at AI from a developer's perspective. And that is the fact that AI, even if we are an experienced developer, enables us to build

things we previously weren't able to build. And also important, it can help us learn new things and expand our skill set. Now I will say there also is the danger of going the opposite direction. There is the danger, and I've talked about this too, of relying on AI too much, of not understanding the code it produces, maybe of not really looking at it and of ending up in a code base where you don't know the code, where you don't understand what's going

on. Uh, that's definitely not the direction you But let's say I wanna build my own web-based image editor, something trivial where I maybe can just the saturation of an image and save that as a new image. Or I wanna build my own very basic video tool that, uh, encodes a video, maybe extracts the audio from a video. I wanna build my own tool because I wanna an overall workflow or anything like that. Now previously, I'll be honest, these are things that would've

taken me quite some time to build because I had basically no experience with working with the Canvas API or of image manipulation in the browser. I had no experience with MPEG. So these are things where I would have to dive into the documentation, read tutorials, watch videos. And whilst that all is fun and builds up some knowledge and is therefore in theory important, it's also something where I probably wouldn't have had the time so I wouldn't have done it and I would've found other solutions to my problem, so

everything's good to some extent. But I do believe that it's now actually a better time to be a developer because we can now build any kind of utility tool, any kind of workflow we wanna build, even if it involves things or skills that we don't have yet. Because if I need a, a tool that extracts audio from a video, I can just prompt AI to build it for me and I very likely get a tool

that works. Is it perfect? No. It will probably not cover all possible edge cases, it will probably be buggy to some extent, but it might be good enough for me. It might be good enough for me to get the job done which I want to get done. If it fails on a four-hour video but works on a ten-minute video and I only have ten-minute videos, then this is not a bug or a problem I need to tackle. So I don't need the perfect tool, I just need a tool that's good enough. But isn't that vibe coding?

Well, to some degree it is, but here's the interesting thing, me. I really enjoy the process of building utility tools, little helpers that I can use and then I enjoy the part of diving into the code and doing some research of what's happening there. But since I already got something working, since I already have that initial solution, I don't have to dive into the docs and try to find out which parts are important for me. Instead, I can just read more about

the, the methods, the tools, the, the functions that are being used in my code and understand what exactly And that allows me to build up an understanding of how that technology, that library, or whatever is getting used in my code works under the hood. And I've learned a ton about working with Canvas API, about web animations, about tools like MPEG, and many other things just because I built own little helpers. And these are not just fun projects, by the way. These are actual things that then in the end might find their way

into an actual product I'm building. Obviously then polished and with, um, with more knowledge from my side then because of course once I build something production for other people to use, I 100% want to make sure that there are no bugs in there, or at least no bugs, uh, I, I know about and I wanna make sure that it's stable, that it's fast, that I use common best practices. So of course I will then take that time to polish it and to learn more about it. But for getting started with the learning

process or if we're doing some one-off tasks, I think we're living in the best time possible because AI is a big enabler there. By the way, also for example, if we're talking about technologies or programming languages we're not that good in. Now, for example, I'm way better in JavaScript than I am in Python also because I haven't written a lot of Python code for the last three to four years. Lots of small utility scripts and workflows,

definitely, but nothing complex. So I don't have any expert or deep expert level knowledge there. Something I wanna change again, But it is what it is. Here of course, AI can also help me get stuff done and then either I remember the syntax I see and I remember what's happening there or I can then again dive deeper. And I think that's a very valuable thing or advantage we get out of AI, because it allows us to do stuff that otherwise would've been

impossible or maybe just not worth our time and also grow our skill base. I think that is the, the important part pure vibe coding where you don't even look at the code, where you don't care about the code. I care. I like learning. And as I've said in other episodes as well, I can only recommend going deep, uh, as a developer. You want the deep knowledge, you wanna be better than AI, you wanna be an expert in certain matters and you wanna understand what AI is

doing and always get to a level where you can correct AI or steer AI. Because as long as that's the case, you'll have, uh, a reason to get employed or whatever your goals are. You don't wanna be on the same level as You wanna be above it at least in certain areas. Obviously with the broad knowledge AI has, you can't beat it everywhere but you can beat it in certain domains and it can be a great enabler.

Open the transcript file

Hosts and Guests

Nobody is credited on this episode yet.

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. We will have to accept AI-generated content

    Oct 15, 202612 minAudio

    I think we'll have to get used to (and accept) AI generated content. Not to slop though.

    • Apple Podcasts

    Credit the people on this episode

  2. Is software dead?

    Oct 13, 202612 minAudio

    There's a lot of talk about software being dead. Unsurprisingly, it's complicated.

    • Apple Podcasts

    Credit the people on this episode

  3. GPT 6 Astra - Good Beyond 3D?

    Sep 9, 20268 minAudio

    GPT 6 Astra was released. It's a good model, I have to say. Especially for 3D work it seems to be a real game changer. But due to all the hype, you may be disappointed...

    • Apple Podcasts

    Credit the people on this episode

  4. You may ignore Omarchy but not its impact

    Aug 26, 20268 minAudio

    Omarchy got a lot of hype and visibility recently. But even if you don't care or don't use it, you shouldn't ignore it.

    • Apple Podcasts

    Credit the people on this episode

  5. SvelteKit 3, Solid 2 - Do they matter anymore?

    Aug 18, 202614 minAudio

    We're not going back to the JS framework wars. BUT new frameworks and framework versions are important. For a different reason now!

    • Apple Podcasts

    Credit the people on this episode