EP051: Vibe Coding For Post Production

00:00:00:00 - 00:00:15:19
Robbie
Hey everybody, welcome back to another episode of The Offset Podcast. And today we're talking about that hip, cool phrase; vibe coding and how it pertains to post-production workflows. Stay tuned.

00:00:15:21 - 00:00:35:00
Joey
Support for this episode comes from Flanders Scientific and the XMP 270 and XMP 310. The accessible, lightweight and versatile monitors helping to bring HDR monitoring on set while also being very well suited to post-production work. Learn more at FlandersScientific.com.

00:00:35:02 - 00:00:43:20
Robbie
Hey everybody, welcome back into another episode of The Offset Podcast. I am one of your hosts, Robbie Carman. And with me, as always, is Joey D’Anna. Hey, Joey, how are you, man?

00:00:43:21 - 00:00:45:22
Joey
But hey everyone.

00:00:46:00 - 00:01:05:15
Robbie
So, Joey, I just have to apologize up front. I'm probably going to use the word coding a lot here when you, it drives you absolutely insane. And we should be using programing. So I apologize to you and our audience. I'm just going with the phrase the jaw, and that is vibe coding.

00:01:05:17 - 00:01:23:10
Joey
And, yeah, yeah, I hate the term coding because it's not a real word. You're not coding anything. You're not encoding a message. You're not encoding. It's wrong. It's called programing. And I don't even know what a vibe is. So I don't know what a vibe coding is supposed to be.

00:01:23:12 - 00:01:24:16
Robbie
So, so, so....

00:01:24:16 - 00:01:39:12
Joey
This is going to be me screaming at the cloud saying, I don't like these newfangled words. Dear newfangled words or not, there are still powerful workflow technologies available to us now that are new and we should talk about.

00:01:39:14 - 00:01:58:22
Robbie
Yeah, totally. And and our dear viewers will understand your get off my lawn attitude. I mean, after all, this is our 51st episode. So if they haven't gotten used to, you know, Joey getting on a soapbox about something especially highly technical, computer based, concepts, then, you know, you should go back and watch some previous shows because you're still on my.

00:01:58:22 - 00:01:59:22
Joey
Lawn at this point.

00:01:59:22 - 00:02:16:19
Robbie
Well, yeah, there's some there's some good rants to be had. But anyway, before we dive in, the same usual housekeeping as always, you can find us on social media just by heading over to Instagram or Facebook. Searching for the offset podcast, you can find our complete library of episodes, including show notes and in some cases, some additional downloads and such.

00:02:16:20 - 00:02:33:04
Robbie
Over at the offset podcast.com where we have our whole library. And you can also find us, of course, on any major streaming platform like Spotify, Apple Podcasts, and the video, version of the show is obviously available on YouTube as well, where we have a lot of you, chiming in there, please drop us a comment.

00:02:33:04 - 00:02:49:15
Robbie
Like subscribe to everyone on the show. Tell your colleagues and friends. Every bit goes a long way. So, Joe, let's start. I sort of want to talk about a little bit of the Wayback Machine in a personal sort of anecdote about this. And we're not going to have to go that far right back in the way back machine.

00:02:49:17 - 00:03:09:23
Robbie
A couple years ago, probably five, six, seven years ago, I started realizing because I was seeing I, you know, at the time, I was doing a lot of international travel, a lot of speaking at events, you know, conferences and things of that nature. And I kept encountering this type of person that was involved in post-production somehow.

00:03:10:03 - 00:03:30:02
Robbie
Right. They were an editor. They meant maybe an engineer here and there. They were colorist, they were DP. And, you know, you'd be talking to them and they'd randomly just drop, oh, this app that I made, oh, this, this, this tool that I made. Right. And yeah, sure. Like the really sort of involved people in our industry have always done this level tinkering.

00:03:30:02 - 00:03:47:16
Robbie
Right. Something's not available. I'm going to make it myself. And it used to be they did that with, you know, metal and plastic bits and a whole bunch of solder and you know, like physically putting something together. And what I realized about 5 or 6, seven years ago is that that's shifted largely to application development. It's, shifted largely to programing.

00:03:47:18 - 00:04:10:03
Robbie
And so you know, I was that's when I first started hearing it. But at the time, this was people who had invested a lot of time in learning Python, JavaScript, you know, C or C plus or any other range of languages and toolsets out there. And I started I tried to get into that stuff, man. And, you know, my brain just it I just it's it's a limitation, let's put it that way.

00:04:10:03 - 00:04:29:21
Robbie
Like it's I, I get the, I get the idea of order and syntax and or whatever and calls and responses and I get it on some level, but I just wasn't me. You know, there's there's some people, I'm sure you've encountered these people who can look at, programing language or I'm going to use the word code here or, you know, look at, look at a whole thing laid out in front of the bingo.

00:04:30:02 - 00:04:48:19
Robbie
Oh, yeah. I totally know what's going on. It's like they're reading. You know, it always reminds me of, like, the, you know, the first matrix, right? When all the numbers are streaming down the screen and somebody is like, oh, see that guy running right there? And you're like, what? Am I crazy to think that that's like kind of old school programing takes a little bit of a different level, different mindset to kind of get your head around?

00:04:48:21 - 00:05:16:19
Joey
Yeah. And it's an important concept that I think a lot of people don't really know how to label, but the, the because I've got a pretty decent programing background. I'm not the greatest program in the world, but I've always made my own tools, made my own kind of work flow enhancer, stuff like that never made them to the level where they were good enough to really share among the world and support, because support is a whole nother thing that you need to get into if you start selling software.

00:05:17:01 - 00:05:42:20
Joey
But I have since early, early days, you know, people have always there's always a fun story that I bring up is that I invented Dropbox three years before Dropbox Incorporated existed. Which is true. You can go to the Wayback Machine and Internet archive.org, and I can prove that to you. But, you know, even 20 years ago, I was writing, like, some web based applications to optimize the workflows for the post house.

00:05:42:20 - 00:06:21:18
Joey
I was working with at the time. And, what you're really talking about is a concept called abstraction, and it's something that's used in programing, but it's also something that I like to think about in kind of all things. What abstraction is, is you take specific things and you generalize them with programing that happens with programing languages, that happens with device drivers, that happens with what's called abstraction layers, where okay, every for example, every single software that uses a black magic hardware interface doesn't talk directly to the black magic hardware.

00:06:21:21 - 00:06:45:11
Joey
They talk in a standard language. They basically say, hey, I know how to send video to a device. And then Black Magic writes the software that actually handles well. Okay, this is a deck link AK this is a deck link 4K. This is a mini monitor that's why After Effects DaVinci resolve, Premiere Media Composer none of them need to know the specifics of your Black Magic output hardware.

00:06:45:13 - 00:06:56:05
Joey
They just know we're using the Black Magic API that then abstracts all the technical nonsense that you don't want to have to do, and then handles it.

00:06:56:07 - 00:07:17:12
Robbie
So before we before we move on, Jerry, can you just real quick, because I think people have heard these terms before. API, SDK like what are those terms mean? Because that's the sort of abstraction layer you're talking about in sort of the, the nice package that companies put their abstraction layer in one of those term, because you hear those terms all the time, go get the API key or go get, you know, or download the SDK.

00:07:17:12 - 00:07:18:14
Robbie
Like, what does that mean?

00:07:18:16 - 00:07:52:20
Joey
Yeah, that's actually a really, really good point because, you know, people might not know what these acronyms do. SDK is an API specifically SDK is a software development kit and an API is an application programing interface. People will sometimes interchange these things, but they're actually pretty different. An SDK is a set of libraries and base level source code and examples and ways of doing things that lets you use someone else's software.

00:07:52:23 - 00:08:22:03
Joey
For example, Red provides an SDK that they give to Adobe, they give to black magic, they give to avid, they avid, Adobe or whatever will write calls to the libraries in their software that says, hey, decode this AR 3D file and then give me back the image. Okay, so you're using Red's software intellectual property, but you're actually inserting it into your software for the kind of tools we're going to be talking about.

00:08:22:04 - 00:08:48:20
Joey
Yeah, we're probably not going to be doing stuff like that. What we're really going to focus on in a lot of cases is an API where you're using software to give commands to something else and get data back, right. We're not actually, for example, if we were talking to Frame.io to manage some assets or if we were talking to DaVinci resolve also to manage some assets.

00:08:48:20 - 00:09:00:23
Joey
Right. We are not writing DaVinci resolve into our program. We're not writing Frame.io into our program. We are just communicating with those outside entities. That's what the API does.

00:09:01:01 - 00:09:20:09
Robbie
And I think that's a really important, really early distinction to make as you go down this path. Is that you inevitably and it will, as I will explain later, you'll get the potential for frustration exists because you're like, I want to do something, but it's not working, or I can't do it. And that's not always bad logic, that's always bad thinking.

00:09:20:09 - 00:09:41:05
Robbie
That's not always bad programing. That can be as simple as this tool that you're trying to integrate with and get something to do doesn't expose these bits, these API, calls or, you know, hooks to be able to hook into, to do that very thing. And in fact, if you think about it, it's sort of make sense, right?

00:09:41:05 - 00:10:03:10
Robbie
If you if you are a big company and you've spent millions or billions of dollars developing software, you're not all of a sudden just going to go, hey, sure, Joe Schmo, do whatever you want on top of to modify our software, etc. that's why if there are certain things that like, you know, in our in our world and, you know, resolve, people like, oh, I'd love it if black magic would just expose that.

00:10:03:10 - 00:10:22:19
Robbie
And what they're trying to say by that is, I wish that black programmers of black magic would build in these API hooks so we can direct, resolve or whatever the tool is to do something. And sometimes that is for strategic money reasons. Sometimes that's just because nobody's ever thought that somebody would need that use or, or do something like that.

00:10:22:19 - 00:10:46:14
Robbie
So that that's an important distinction right now, I think to make is that just because as we're going to discuss, coding has gotten in programing has gotten in some ways, in some ways not much easier. You are still at the behest of the ecosystem around you that you're trying to to, to control with this programs, because not everything's going to expose these hooks to do exactly what you want.

00:10:46:15 - 00:11:10:21
Joey
Yeah. Because specifically what we're talking about with writing our own tools for post-production workflow, obviously, we're going to be connecting to a lot of different existing tools and existing workflows. That's the whole point, right? We're not talking about I'm going to write my own color corrector here. I'm going to write my own non-linear editor. If you want to do that, go with God and joy.

00:11:11:02 - 00:11:13:01
Joey
But.

00:11:13:03 - 00:11:30:03
Joey
For for practical purposes of what we're talking about today, making our post-production workflows faster, easier, more flexible with custom software, we're really talking about using APIs to do clever things across multiple existing software and workflows.

00:11:30:05 - 00:11:49:12
Robbie
Yeah, totally. So the thing I want to get into is this distinction between and and I'm going to use this term just because it's something that I've heard, but not necessarily the right way to support it, but it just kind of I give the old versus new or the, the hybrid approach is some some legs here. And that's sort of what is vibe coding and what's the opposite of vibe coding.

00:11:49:15 - 00:12:05:19
Robbie
And I will just I have in been in the habit recently of calling the non vibe coding stuff and I'm not coding, but I know that too. I know, I know, I know you hate that. That's cheesy. Somebody I know and is well respected in the industry gave me that term and I was like, oh, it kind of makes sense.

00:12:05:20 - 00:12:27:00
Robbie
All I'm going to say about analog coding, whether you hate it or not, hate it. It's just traditional programmers, right? People writing the actual code themselves, bug checking it, you know, running debug algorithms, looking at it, syntax, etc. versus sort of the new fangled way of vibe coding and vibe coding is a, a relatively new thing.

00:12:27:05 - 00:12:47:07
Robbie
The Google machine tells me that this word, was sort of coined by this guy Andre Karpathy, in February of 2025, actually, and he posted about it on Twitter, and he is just, his definition is a style of programing where you essentially give yourself over to the AI, describing what you want in natural language and just go with the flow.

00:12:47:12 - 00:13:17:02
Robbie
You're not carefully reading or understanding all the code that the AI generates. You're just kind of vibing with it and iterating based on what works and what doesn't work right. You can see the steam coming out of Joe's head right now. Okay, so let me give you a practical example of something like the vibe. Could it? So let's just say that you wanted to, I don't know, do something really simple like super simple, like when you log into your Mac, you want, a couple network drives to automatically mount, right?

00:13:17:04 - 00:13:32:03
Robbie
A lot of people do that through, you know, the built in OS, but you could write like an Apple script. That's how I do it, right? I have a little Apple script. So through some trial and error, I wrote an Apple script trying, you know, various I didn't know Apple script very well, some syntax whatever. And it took me five, six, seven, eight iterations to do it.

00:13:32:08 - 00:13:52:14
Robbie
But then I realized, oh, but now I want it to give me a notification when it mounts these drive. And like, I got down this whole where I was sort of starting to go like, okay, I'm learning, I'm building, I'm learning, I'm building and making mistakes. And next thing you know, I spent like, like a stupid amount of time, like four hours trying to get, you know, notifications on two drives to pop up to mountain.

00:13:52:14 - 00:14:14:13
Robbie
Like what? I'm like, this is stupid. I go on cloud or ChatGPT and say, hey, here's what I'm trying to do. Can you do it for me? Thinks, bam, here's your Apple script, put it in your startup items done right. So I literally in just natural language words describe to the system the AI. In this case it was I think it was quite at the time, in explaining what to do.

00:14:14:13 - 00:14:39:01
Robbie
And it spit out something that I had previously spent a few hours trying to figure out. That's kind of vibe coding, right? And that's like an ultimate simple where this can extrapolate like leaps and bounds, extrapolate exponentially how complicated it is. But that's basically the gist. Using natural language to tell this, the machine, the AI or the platform that you're using, we'll get into those in just a little bit.

00:14:39:03 - 00:14:43:11
Robbie
Hey, this is what I'm trying to accomplish. Can you help me do it and spit out something?

00:14:43:13 - 00:15:10:05
Joey
Yeah. And I've kind of always said since these AI and LMS kind of first started becoming usable, that I consider them to be kind of the highest of high level programing languages. When you talk about the level of a programing language, you're talking about the distance to the hardware, right? Again, how much abstraction are we doing between you, the operator, and the actual.

00:15:10:05 - 00:15:16:06
Robbie
This is that next level up, right? This is like you're taking something that's already abstracted through SDKs and APIs.

00:15:16:08 - 00:15:46:14
Joey
And it's layers upon layers upon layers. You know, early days, the first computers were defined. You know, how do you go from, for example, a calculator to a computer? A calculator has a set of specific ins and outs, essentially, right. A computer follows instructions. So the first computers were programed with very, very simple low level instructions that directly manipulated things like memory and CPU instructions, stuff like that.

00:15:46:19 - 00:16:09:19
Joey
Then we wrote assembly language to kind of abstract that a little bit easier. So you would say, okay, instead of pulling up the actual instruction value for what move memory is, now it's move, we can move this memory, but you're still really low level. You're talking about what bits and bytes of memory to put in different places, and then.

00:16:09:21 - 00:16:10:03
Robbie
You can.

00:16:10:03 - 00:16:11:13
Joey
See how that can be you.

00:16:11:17 - 00:16:14:15
Robbie
You can see how that extrapolates up. Right. That like but then.

00:16:14:15 - 00:16:39:14
Joey
We go and we write languages like C and C plus plus that have almost English looking syntax for while if things like that. And that again gets compiled down to machine code and then binary and all that stuff later on. But for the programmer it's easier then we came up with scripting languages Python, JavaScript, etc., where you don't have to think about what the computer's doing.

00:16:39:16 - 00:17:04:02
Joey
The back end of the programing language is handling things like memory management and stuff like that. Great. Easy. Now we get to these limbs where you don't actually need to write the instructions in a specific language. You can write the logic out in English and ask it what to do, and it will extrapolate. And this is where it's important to kind of think about what these limbs are good at and what they're not.

00:17:04:03 - 00:17:31:17
Joey
What they're really good at is looking at gigantic data sets, because that's what they were trained on. Like you said, you were trying to write a specific, easy little apple script to get notifications to work. Are you going to sit through reading all the documentation of how Apple Script handles notifications, or was Claude already trained on all that documentation and examples and such, and can just easily say, okay, he's asking for a notification in this format.

00:17:31:20 - 00:17:38:13
Joey
This is what a notification code looks like in Apple script. Boop boop boop boop boop boop. Put those two things together.

00:17:38:13 - 00:17:39:14
Robbie
And and if it's the.

00:17:39:14 - 00:17:41:10
Joey
Exact instructions you want.

00:17:41:12 - 00:18:05:03
Robbie
And if it's well trained, it also can. So so the interesting thing about this is that, I to say in a slightly different way, these toolsets are only going to be as good as the training that they receive. Right? And a little later on, we'll talk about some because everybody knows about the ChatGPT and the clods of the world, where those are perfectly fine for doing base level processing.

00:18:05:05 - 00:18:30:19
Robbie
But there are platforms that excel at much more sophisticated full stack programing, and the reason that they're more sophisticated and more functional than, say, a ChatGPT or cloud or whatever is because they've been trained on this specific type of thing with a lot more nuance and a lot more information than, say, a generalized, you know, public, kind of, you know, system like cloud or ChatGPT does.

00:18:30:23 - 00:18:55:12
Robbie
That's not saying that there's, there's, there's major I can't do a relatively good job. But if you were, you know, like AppleScript or whatever, fine, fine. If I was getting into something where like, oh man, I have this specific FPGA board that I'm trying to, you know, I, I bought on, you know, AliExpress or whatever, and I'm trying to program and it's all hex code like, yeah, that's probably not going to work too well with these.

00:18:55:14 - 00:18:56:16
Robbie
Like these big these big.

00:18:56:16 - 00:19:23:16
Joey
And this is an important thing to kind of remember to when you're dealing with Lims, is they only exist in the world of already solved problems, right. They're not going to come up with new algorithms. Okay. You want to have, you know. Right. Have Claude write you a program to search through all of your scripts and, you know, extrapolate certain things for your producer or something.

00:19:23:16 - 00:19:55:00
Joey
Great post-production work. Work. Workflow use case. Okay, fine. But if you want and it's going to be great at that because all of the kind of key intellectual parts of what you're asking it to do exist out in the world already, you are not going to ask Claude or ChatGPT or anything else how to make cold fusion work, or how to get a and or in a more, you know, reasonable example, how to optimize a sorting algorithm for performance on a new CPU that they don't know about.

00:19:55:01 - 00:19:56:05
Joey
You know what I mean?

00:19:56:07 - 00:19:57:03
Robbie
So can I tell you some.

00:19:57:03 - 00:20:20:07
Joey
Optimize it can do has already been done. If you are trying to come up with like, okay, color science, for example, if you're trying to come up with some kind of new and novel color matching function that nobody's done before, no, these limbs are going to have no idea what you're talking about because there's no training data surrounding it.

00:20:20:11 - 00:20:44:22
Robbie
Support for this episode comes from Conform.Tools. Conform.Tools allows you to translate timelines between Premiere and Resolve and other NLEs, while automatically solving common issues that normally need to be fixed by hand, avoid time consuming trim and transfer issues, and securely send large media files to collaborators at a fraction of the size and in minutes instead of hours.

00:20:45:00 - 00:21:10:11
Robbie
With a growing toolbox of features, let Conform.Tools handle the tedious stuff so you can focus on the creative. Built by post professionals. Conform.Tools helps editors, colorists, and conform artists move faster and finish stronger. Learn more at Conform.Tools. So what's. In short? One of the things that I think is an interesting development as these two. So obviously people over decades have built up their skill sets in programing.

00:21:10:11 - 00:21:30:22
Robbie
And there is, you know, a huge repository of talent of code, APIs, UX, whatever. Along come these OEMs and we get into this vibe coding world where it's just speak your mind, create a tool. I've always been interested where that combination exists, right. Because it like anything else like this, there's no such thing as auto magical perfection, right?

00:21:30:22 - 00:21:50:22
Robbie
Like it doesn't like you're not going to just do something. And so like, even in my own journey over the past year or so, I've been let down a lot, a lot of holes where it's just been like, oh, okay, we just spent three hours going through this and you forgot about this, or you hallucinated this, or that's not a thing like, you know, or whatever.

00:21:50:22 - 00:22:11:20
Robbie
There's there's a myriad of problems with there. So it got me from the very beginning thinking about, well, what do real programmers do in this? I mean, do they just revert back to the old ways and do everything by hand? How do they leverage? So I started looking into this and I started talking to, quite a few people, and one conversation popped out.

00:22:11:20 - 00:22:34:23
Robbie
I had a, we have a colleague that works at one of the the biggest post-production and production installations in the world, and I was asking her about, you know, she shared her role there. She was, hiring people to do sophisticated, you know, programing work. And she said almost all the programmers that she's interviewed over the past, you know, a half or so, you know, half a decade, they use both.

00:22:35:00 - 00:23:02:10
Robbie
They are doing, repetitive, difficult, tedious tasks with Lmms or some other sort of AI, but they are still doing the ideation. The buggy, like the, the the, the process, the thinking, the big picture, the like. I want to do this kind of thing. They're still doing a lot of that work by hand. And utilizing the LMS as just another toolset, almost like another library in their world.

00:23:02:10 - 00:23:19:02
Robbie
Or for us, it would be like another plug in or something like that to try to get to push the ball faster, because to them it's not about they're going to arrive at the same point, probably. Right. Maybe, you know, likely it's just whether it's going to take them three months to do that or it's going to take them three weeks to do that.

00:23:19:02 - 00:23:38:21
Robbie
Right. And that's where I think that a lot of, you know, people who already are good at programing are looking at these tools and coding. It's like, okay, look, I can get 90% of the way there with this tool, doing what I want, you know, like doing it automagically and then knowing with my knowledge I can go in it that that's BS.

00:23:38:21 - 00:23:57:19
Robbie
Nope. That's right. This is inefficient. You know, they're double checking that work. And that really makes a lot of sense to me, right? Is that, you know, both people like me who are newbies at it just go, wow, this is amazing. I can create this thing. But even in my short time, I've gotten more into it. I mean, like, hold on a second, like that, why are you doing it that way?

00:23:57:19 - 00:24:24:06
Robbie
That doesn't make sense. Like, think about it this way. And the more knowledgeable about it, it's actually like this. Weird. I don't even know what it would be like. Inverse square law or something. Right? Where like the more you get into vibe coding in a weird way, the more you get into traditional programing because you're like you're wanting to like, double check it, figure it out, understand it better, rather than just accepting it as, like the only way of doing it, if that makes sense.

00:24:24:08 - 00:24:49:03
Joey
Yeah. And this is kind of the most important concept I think, that anybody can get when it relates to using Lmms for programing or anything else actually, which is the universal truth of garbage in garbage out. You know, we deal with it in color grading. You give me DV cam footage from 1999 that's overexposed. I can only do so much, so much.

00:24:49:05 - 00:25:21:03
Joey
You give the LM something stupid, like write me the next cool app that's going to make me rich. It's not going to give you anything actionable. So the most important thing of any of this is to be able to conceptualize and describe the total ality of the problem you're trying to solve. And when I say totality, I mean, how does it handle all different kinds of inputs?

00:25:21:03 - 00:25:43:13
Joey
How does it do x? What does it do with Y. What do you want it to? How do you want it to be structured and to ask the right questions and to give the right terminology in the right structure? You need to understand how computing works. Otherwise you're going to, like you said, go down these rabbit holes of hallucinations that don't get you anywhere.

00:25:43:13 - 00:26:06:00
Joey
So if you can clearly define the problem and I mean for mostly to the point of not just, okay, write me something that will take my idols and clean them up for how my client wants them. No, no, no, you need to be able to say, okay. The EDL consists of a tab separated list with source timecode, which record timecode here for our application.

00:26:06:00 - 00:26:28:09
Joey
We might not care about source timecode, but you still need to have it in the file. You might need to explain stuff like that. You know you need to dig down to the the base level concepts of what you're asking the computer to do. And then, yeah, the Lem can do a really good job of cross-referencing. It's gigabytes of training data and putting all those pieces together 100%.

00:26:28:09 - 00:26:51:18
Robbie
And it's actually really funny to me that that part of this concept, this, this, this, this movement, if you will, is no different than the analog, you know, regular programing like that, like there's some big picture concepts that are unique. So as you said, clearly defining the problem in a way that's more than just as you said, you know, make me some cool things, like really explaining it step by step.

00:26:51:22 - 00:27:11:20
Joey
I'm just defining the problem for the Lem. You should be able to sit down and draw out a block diagram of exactly what you want this software tool to do by yourself first. That way, when you start, because you're not going to try to one shot the whole thing and say, okay, give me this tool that does XYZ and all these different things, right?

00:27:11:22 - 00:27:49:16
Joey
You're going to probably want to break it down, be like, okay, here's the overall concept. Now write me a module that does this EDL processing. Write me another module that handles file IO to send things to Frame.io or Dropbox or whatever. Like that. You know, it's easier to break the problem down into smaller chunks, that you can then define those smaller chunks in their totality, but in your head as kind of the virtual product manager, you need to understand what every component of this imaginary tool is going to do and describe how they all connect, not necessarily all in one easy description.

00:27:49:18 - 00:28:07:03
Robbie
Totally. And I would add on to that. It's also like there's a I know this is going to sound funny, but there's a level of like hubris breakdown that has to happen here to get the most out of these tools, right? Like if you're just like, oh, well, of course I know this or that. Like, I think it's also important as you're working through these problems.

00:28:07:05 - 00:28:27:00
Robbie
So to define and be honest with the, the, the platform, the Lem, what you do know and what you don't know. Right. So like if you know, like, hey, I know that this tool uses I'm just picking one out of the hat multipart chunks to do an upload. Right? Like I know that, but I don't know how encryption works for the multipart uploads.

00:28:27:04 - 00:28:42:05
Robbie
Can you tell me how like, can you build that, like just kind of, you know, being aware of the things that you don't know and the things that you do know? I think also, really give that, you know, the process a lot more validity. And the other thing I would add there too, is that, like.

00:28:42:07 - 00:29:09:01
Robbie
I can't discount the idea that the more knowledge that you have about a subject, the better off you're going to be as an air Quotes vibe coder, right? So if you understand, like in the example I just gave, how HTML works, how CSS works, how, you know, basic JavaScript works or whatever, like you're going to be a leg up to know when that limb is doing something stupid.

00:29:09:04 - 00:29:28:12
Robbie
It's hallucinating. Like, it just can't possibly work like that. Like, I'll give you a great example of this. A couple weeks ago, I was, I was sick. I had, I was, you know, in bed for a week or whatever, and I was just playing. I was like, oh, you know what I mean? I'm going to build a a new dashboard and home assistant for, my, my ubiquiti unified network.

00:29:28:12 - 00:29:49:18
Robbie
Right. And like, instantaneously, it gave me this, like, beautiful dashboard. And I'm like, oh my God. And then I'm like, hey, this doesn't appear to be changing. Oh, that's just a placeholder because it looks cool. Really like you. You can tell me the information from this device. Nope. No access to that device. I'm just like, it just looks cool, right?

00:29:49:18 - 00:30:13:21
Robbie
And, like, very easy. I'm like, very quickly. I'm like, oh, so you don't have access to this sensor on this switch? Like just knowing some of that terminology, it's like, oh, you're correct. I don't have. But I do have access to this sensor, which we call a traitor. Like, I'm just saying, some of that baseline knowledge about whatever you're trying to do, like even if it just conversant knowledge even can really go a long way in helping, build a better tool.

00:30:13:23 - 00:30:50:06
Joey
Yeah, even the best LMS in the world, even a Star Trek level computer human interface that is like, way beyond anything that we can even conceptualize. Right? If that existed, it would still only be as good as your ability to describe a problem and describe a concept. Right. And that's the like basically take your Lem and say, if I could just hire a programmer who is very good at this one particular niche thing to do this module, what would I be telling them?

00:30:50:08 - 00:30:57:16
Joey
Right. It's the exact same skill set of managing people, except you're managing robots.

00:30:57:18 - 00:31:20:17
Robbie
Right? And the last thing you said there, is it really important to you? I think the other the other part about this is, evaluating output. I think is really is a really interesting is really interesting part of this because like, you'll get something out of this, but then what, like your job as the human is to look at it, like, and I've found in my experience too that like, okay, fine, it outputs something for me.

00:31:20:17 - 00:31:42:19
Robbie
I inside deploy that I look at it and I'm like that leads to more iteration, more testing, more whatever. And here's the danger of it, right? Is that like all of these models and platforms, they have role to I mean, not for most most people. They have limits in the, how much you can press them, how much heavy lifting they're going to do in any given time period.

00:31:42:19 - 00:32:03:05
Robbie
Right. So like you'd be it's you will save yourself money and be more efficient too, if you can do this in an organized this kind of work in an organized fashion. Right. So instead of like you get an output from an LM for something, you deploy it and instead of going, fix this, give me a new file, fix this, give me a new file, just like you would like a program.

00:32:03:07 - 00:32:27:22
Robbie
Product manager would in the real world, at a regular software company, they would build a report that says, here are all the problems I'm ranking these problems and the orders that they need to be fixed based on severity. This is what I would like to see the outcome be and feed that back. You'll actually end up being a lot more efficient with the costs in the use of your LM, than just trying to one off and iterate things as they come up.

00:32:28:00 - 00:32:53:11
Joey
Yeah, and that's where I think a lot of people fall down is they don't know how to essentially beta test. Right. This is a specific skill to computing that I think a lot of people need to kind of get better at, which is how do you test something that you're not 100% sure of? What that means is, and there's something LM can't help you with, this is something that Google can't help you with.

00:32:53:11 - 00:33:15:16
Joey
This is something you know you need to know. Again, you're assuming you already know the totality of the problem you're trying to solve. So you have it mapped out in your head or on paper what this tool does. Now, how do we test it? Well, first we feed it ideal things. We feed it the most easy possible input, the most easy possible scenario, and make sure that works.

00:33:15:16 - 00:33:35:17
Joey
If that doesn't work well, we got to start figuring out the base level stuff, right? But then what you got to do is you got to start testing things, what we call boundary conditions, where okay, everything makes sense, except I'm going to do one thing that might be unexpected. I'm going to put a negative value here where it's only expecting a positive value.

00:33:35:21 - 00:33:55:17
Joey
I'm going to put a special character in this string for the name of the timeline that this tool is going to manipulate, I'm going to see how it handles drop frame versus non drop frame timecode. I'm going to change the frame rate of this one source. And the way you do this testing needs to be both organized and methodological.

00:33:55:17 - 00:33:57:05
Joey
Mathy.

00:33:57:07 - 00:33:57:21
Robbie
Well I got.

00:33:57:22 - 00:34:21:22
Joey
Particle methodically sonically is the word. Because just like any other kind of troubleshooting you want to reduce the number of variables. So you built this awesome tool that you vibe coded to handle some kind of post-production task, let's say. I mean, does some kind of manipulation to a timeline. Okay, great. Works on your first couple timelines. You test it on.

00:34:22:00 - 00:34:41:22
Joey
Cool. Now what's the next step? We need to go through and remove variables. We need to go through and test it with every frame rate okay. And test it with every frame rate, but nothing else changing. Which means you need to go into your NLE and make five identical timelines of different frame rates. Right. Test all of those, see what happens.

00:34:42:01 - 00:34:59:21
Joey
And then that will introduce things problems that you need to solve. Okay great. Now we've got the frame rate solve. Then we figure out things like drop frame non drop frame different timecode formats do the same thing. Then you do great okay I'm gonna try it with different resolutions that I'm gonna try with different sources. And I'm going to try it with different naming.

00:34:59:21 - 00:35:15:21
Joey
But the big thing here is we're looking at the structure of what we want the tool to do. And we're finding out what we can test that only changes one variable. We're not going to say, okay, I've got five different timelines from five different clients. I want to run through this tool. Just throw them willy nilly out there.

00:35:15:22 - 00:35:18:01
Joey
You're going to end up with 15 different.

00:35:18:01 - 00:35:20:01
Robbie
Errors because you don't know what you don't want. You know. You don't know what.

00:35:20:01 - 00:35:21:14
Joey
Aren't able to be tracked down.

00:35:21:16 - 00:35:23:08
Robbie
Yeah. You don't know what you're testing at that point.

00:35:23:10 - 00:35:47:22
Joey
Exactly. So you need to you need to be able to build test cases to input into this tool you're making and understand how to do that, where you're only changing or testing one variable. You want to be able to verify, okay, this timeline going through this tool works 100%, right. That's kind of our base level. Then we change one variable that works 100% great.

00:35:47:22 - 00:36:08:21
Joey
Then we change that same variable again to another thing. Oh that broke. Now we figure out what we need to fix in that path like that pathway. And we figure out how to fix that before we start testing other things and throwing other random stuff at this. So being methodical about your testing is something that the LM can't really help you with.

00:36:08:23 - 00:36:32:03
Joey
What you know, it comes down to you understanding the problem, and nobody else can do that for you. That's how you kind of get from the wow, I just told the LM to write this, and it came out with all this output that actually kind of works awesome. This is really cool too. This is a tool I can actually use in my day to day work and trust, you know, that's how you bridge that.

00:36:32:05 - 00:36:54:11
Robbie
And I and I actually think there's a, there's I actually think there's a couple middle milestone points on that process too. Like, so I'll talk about this in just a moment. One of the examples I want to give is something that I recently built, using this mythology, methodology rather but one of the things I was thinking about and again, I think it's because I know the right questions to ask.

00:36:54:13 - 00:37:18:11
Robbie
So I built it. I built a tool this this, client portal that we'll talk about in just a minute. And. Yeah, eventually, I needed to test it, right. With various. And you've been testing it in various uploads, and and we've found some problems with it. But my point is, even before I was ready to go out and test various uploads and deliverables, I was asking that question like audit level questions like, oh, I notice that you created this link.

00:37:18:15 - 00:37:36:07
Robbie
That seems to be a public link. Is this a security problem that I'm going to be facing? Right? Or like I noticed that that take that took, you know, seemed like it took a long time to produce that that page. Is this the most efficient way to do it? Like and those are just really super high level questions.

00:37:36:07 - 00:38:01:15
Robbie
Right. But like security performance, you know, redundancy fallback if this doesn't work, what happens is this doesn't work. This is somebody presented with a warning. Is it a hard crash like all of those iterations? As you're developing, you need to start thinking a little bit more like a developer. Like, okay, if this goes bad, what happens? You know, if this doesn't work, what happens and you know, or like or how can we get this better?

00:38:01:15 - 00:38:16:04
Robbie
And I think that's I think one of the problems right now, and it's not just unique to vybe coding, it's just our society in general. Right. Is that like something, you know, a computer does something cool and we think it's a messiah. And it's just like, no, no, no no no no no no no.

00:38:16:10 - 00:38:18:04
Joey
Like it's not done. Yeah.

00:38:18:05 - 00:38:34:09
Robbie
You can get very deer and a headlight by some of this output and you're like, oh my god this is the coolest thing. And then you start banging on it and you realize that the oh, I'm just made some placeholders for you like I earlier described or. Oh, really? That secure upload portal. Everything is totally not encrypted and available in the public.

00:38:34:09 - 00:38:36:19
Robbie
Like you probably don't want to fix that. You know, things of that.

00:38:36:19 - 00:38:57:01
Joey
Again, that goes back to you need to have a base level knowledge and you need to if you're trying to get into making a tool that does something. Yes, we we don't have to go down on the the individual line by line code level anymore. That's a great timesaver. But if you don't understand the overarching concept of what you're trying to do, that's where you need to focus your self-education, if you will.

00:38:57:03 - 00:39:12:06
Robbie
So so let's give a couple examples about this. I know you have a couple or yourself that you've you've you've used these tools a little bit. I'll start out with the one that I've been I've been teasing. So about two weeks ago, three weeks ago, I got a, renewal bill from a vendor that we use for our client upload portal and go.

00:39:12:07 - 00:39:31:14
Robbie
Oh, they're raising their prices again. Right. And it was one of those things that, I was using this particular part of the portal I was using specifically with a couple clients. I think you'd only use it once or twice. Like, it was just like it really was turning out not to be worth the investment. And with this stuff in mind, I turned, you know, on a lazy Friday afternoon.

00:39:31:14 - 00:39:58:05
Robbie
When I turned it, I turned to Claude and said, here's what I want to do. Here's the model of what I'm trying to do. Help me do it. And that and that was a pretty relatively straightforward, set of instructions that I gave it. So number one, I knew that I wanted to use storage that was, not local storage, like, not a server running in my basement or whatever I wanted to use something that was globally available at even at edge cases.

00:39:58:05 - 00:40:17:17
Robbie
Right. And so that kind of meant something like S3, wasabi, Cloudflare R2 or whatever. So like before I even plugged, you know, went to, you know, cloud that I, I started looking at, okay, what are the costs involved with these services? Right. Oh, this one has egress. This one doesn't have egress fees. Oh, cool. This one, this one over here.

00:40:17:21 - 00:40:39:08
Robbie
It doesn't charge me a fee whether I like, you know, this, you know, for whatever this operation is, I like that. And I started building this pros and cons lists of the different storage models that I thought could work. Right. I then started thinking about, as you said earlier, like literally like a block diagram. I was like literally just drawing pictures of, okay, if this happens, I want this to happen or whatever.

00:40:39:10 - 00:41:02:19
Robbie
And then it took me like pretty much all afternoon on a Friday to work out the, here's what I want. Here's the tools that I would like to use. Okay. Here's why I would like to use those tools. Is there anything I'm missing in connecting all these tools up? Go for it. Right. And it asked me some questions about various where if you already have an account, are you already signed up for this?

00:41:02:23 - 00:41:21:14
Robbie
Can you go get the API key from this service so I can connect it to this service? Right. And it's like before I even got any output, it was probably a half a day of figuring out all the various pieces. What I was going to need from various pieces, etc. and then when I got it to do the output, that part was incredibly fast, right?

00:41:21:14 - 00:41:50:20
Robbie
Like within 24 hours. And you can attest to this. You were like, what are you doing? You know, I'm not. We're going to break it. All right? I had had it had I sorry. It had the storage. I ended up using Cloudflare Storage for a couple different reasons, but I had Cloudflare Storage and it created a multipart chunk uploader that I could we could embed in our website that put stuff to the cloud storage automatically, but trunking no, trunking it up and encrypting those chunks and pre signing those chunks, just like, say, Frame.io does.

00:41:50:22 - 00:42:06:07
Robbie
So I pop it up in the thing and spit it out at you know, a gig, a second at line speed up to that server. But in that process you started looking at it. I started looking at it going, well, this is stupid. We're going to have to manage users and passwords. I don't like that. I don't want to have to manage something else.

00:42:06:12 - 00:42:31:01
Robbie
Oh, maybe we could integrate it with our existing CRM system. Oh yeah, we can totally do that because there's an API available for the CRM system. Let me go get in. So like I had this idea and initiated it. It then brought like the step two was a huge laundry list of questions, problems and issues that to you said like I wasn't I couldn't roll it out in the current state.

00:42:31:01 - 00:42:46:01
Robbie
I needed to whittle those down. So I got authentication, user authentication working, I got encryption working, I got all these, you know, all these various things like even even to the point of like cleanup, like what happens if somebody cancels an upload? Where does that file go? I don't want to be charged for that. And so on and so forth.

00:42:46:03 - 00:43:01:19
Robbie
And so it was only through some pretty rigorous testing, which we're still in, that we even got comfortable deploying something in just this past week for the first time, after a week of pretty much banging on straight, put it live in front of one, trusted a client and said, okay, try this out, see what.

00:43:01:20 - 00:43:03:22
Joey
Can reduce variables.

00:43:04:00 - 00:43:23:06
Robbie
Right? And they did the first thing. They uploaded a file. And you know what? The first thing I noticed, not that the file successfully delivered, I noticed a problem. I was like, oh man, they uploaded five files and it timestamped all of the file names like it changed the file names. But that's not going to work because it changed the file names.

00:43:23:09 - 00:43:38:02
Robbie
Now the re linking in the project file in the XML they gave me is not going to work. So I spent another hour or two going I don't I like you can put the file the timestamp in a URL but don't put it on the file. Like things like that just kept popping up. Oh, you notice one thing.

00:43:38:02 - 00:44:04:02
Robbie
It does this, it does that. And so I think that there this a little bit of misnomer and what like should be a relatively easy project. That vibe coding just means perfection out of the box. And I will tell you it wrote a JavaScript, worker for Cloudflare that was 1800 lines long. It wrote a HTML, you know, interface or whatever UI part of this.

00:44:04:06 - 00:44:23:21
Robbie
That was another 1700 code. Like, I couldn't have done that work myself at all, right? But it wasn't like the first time it did it. It was perfect right out of the box. Right? It required a lot of questions, a lot of digging. I did, in fact, I actually had to give it at one point because this was a surprise to me.

00:44:23:21 - 00:44:57:04
Robbie
I always thought that LMS were like knowledgeable all the time up to date to like that very moment. Right? So Cloudflare came up with an update to how their UI works, and it kept giving me instructions that were dated, instructions for how Cloudflare worked. Right. And I eventually got sick of it, went to Cloudflare and said, oh, here's the documentation, gave it out to Claude and said, please read this and give me all further instructions with this new, because it was its knowledge cut off at like the end of November of 2025.

00:44:57:07 - 00:45:03:23
Robbie
And here I was in the beginning of March of 2026. And I didn't know about that. Right. So it's always a little bit of a give and take.

00:45:04:01 - 00:45:36:02
Joey
Support for this episode comes from Flanders Scientific's XMP551 and XMP651. The flagship QD-OLED reference monitors that are reshaping modern grading rooms. Their large format and industry leading viewing angles let clients see accurate images from anywhere in the room, and their true HDR and SDR reference performance makes single monitor room layouts possible. When everyone relies on the same display, you avoid the headache of explaining why the client and grading monitors don't match.

00:45:36:08 - 00:45:57:10
Joey
Learn more at FlandersScientific.com. You know when we talk about garbage in, garbage out, if the if the data that it has available isn't current, well, it's not going to work and that's where you need to bring real knowledge of the actual situation, kind of, you know, conditions on the ground to the project and, you know, manage it accordingly.

00:45:57:10 - 00:46:13:05
Joey
Like you did. And that's, you know, that that's where these tools that I know, I, I've probably been more skeptical than most, but I also use them for writing my own tools pretty regularly. You know what I mean?

00:46:13:10 - 00:46:38:01
Robbie
Let's, let's hear about because I know, I know one of the ones that you've done that I just think is just rad is that, there's, you know, you're often involved in these workflows with, spot deliverables and, like, coming up next, next Thursday, next Friday and like, these cut these cut sheets right where it's just like, okay, you got one ad, but it's slightly different, 900 different ways depending on when it's airing in the market, etc..

00:46:38:02 - 00:46:50:10
Robbie
And like that's a lot of manual like tedious work that like, God, I mean, yeah, I know you're getting paid for it, but like, why not just make, you know, work, work some work smarter, not harder kind of thing, right.

00:46:50:11 - 00:47:13:06
Joey
Exactly. So some of the tools that I've done, and I can't go into super details because they relate to very large media companies and their internal workflows. But imagine you get a cut sheet. That cut sheet says, I have a promo that's I have a 32nd version of the 15 second version, and the 32nd. There's a next Thursday at ten, Thursday at ten, tonight at ten, tomorrow at ten next.

00:47:13:08 - 00:47:47:23
Joey
Right. And they all have different tag language and they all need simplest thing ever. Slate's made okay. Write me a script that passes through all of those data points on the cut sheet and uses, you know, ImageMagick to make a PNG slate for each one that's named accordingly. Oh, well, I also have all this information, and this company asks you to write a summary email of every spot that you shipped, including the promo ID number, the tune in the campaign number.

00:47:48:01 - 00:48:07:00
Joey
Oh well, I already had you use all that information to make all these slates. Give me the email I need to send two with that same information. Right. So we're taking all the information in different ways. Just putting it. And it's, you know, really just pointing these inputs to these outputs. But why would I manually do that? God.

00:48:07:00 - 00:48:28:05
Joey
Worst case, actually typing into the thing to make the slate. No no no. Because that's how mistakes happen. Right. But even so copying and pasting the same thing into three different places. Now of course some of this could be mitigated by the place it's being delivered to being more efficient and having their act a little bit more together.

00:48:28:08 - 00:48:48:17
Joey
But as post-production vendors, we know that's never going to be the case, and we know we're going to be hitting a thousand different deliverable formats for a bunch of different companies everywhere we go. So every time we get hit with a weird challenge of, okay, now you need an Excel spreadsheet that has all the in and out time codes of these segments of this show.

00:48:48:17 - 00:49:12:15
Joey
For example, you can literally just say, hey, whatever, Liam, take this EDL, I just output from DaVinci resolve, derive these segment times based on these rules and guess what? It'll actually work. It works really well as long as you can define the problem clearly. That's why earlier one of the things I mentioned was how do you actually make it EDL that works.

00:49:12:16 - 00:49:36:13
Joey
The LM needs to understand things like source timecode isn't optional even if you're not using source timecode. That was one of the problems I ran into with a very specific workflow that I talked about a little bit on some of our other episodes, but basically I was given for a season of shows, a massive amount of handwritten timecode notes from a producer in word docs.

00:49:36:15 - 00:50:01:14
Joey
Right? Not an ideal way to go through your sessions and be like, yeah, oh, I got a typo in this timecode. Go here, figure it out. Typing this timecode, go here, figure it out, put it into ChatGPT. Here's all the emails from the producer with the time codes and the episodes that we need notes for. What I really want is an EDL that has the note as the event comment.

00:50:01:15 - 00:50:23:05
Joey
So the little starred line underneath the event, not the tape name. So that way you can get the full text and I want you to take their timecode, put it in the in and out of the record timecode with a one frame duration, and then copy those to the source timecode and what this is going to do is it's going to give me a readable EDL that I can important to resolve as markers.

00:50:23:07 - 00:50:54:06
Joey
And it took a little bit of iteration of just explaining the output format, being able to clearly define this needs to be a compliant EDL with source timecode, with record timecode with the character limits at the right times and the right fields and everything else. Because it's more complicated than just saying, give me a tab separated list. But eventually, after about maybe 15 minutes of work, I had eight emails of notes that were handwritten all in my timeline and resolved with markers at the exact right places.

00:50:54:08 - 00:51:13:06
Joey
Right? Yep. So that was one of those situations where me, as the kind of director of all this, needs to understand. Everything needs to go in, everything that needs to go out from a conceptual place. And then once I can put that into a little prompt for the stupid robot, the stupid robot goes ahead and does all my tedious work for me.

00:51:13:08 - 00:51:15:12
Joey
That is.

00:51:15:14 - 00:51:33:15
Robbie
All right. I'll give you. I'll give you another a low level example of that, because that's that's brilliant. And I think you hit on a couple things that the biggest one being like, I think everybody, not everybody. I think a lot of people tend to think about vibe coding, programing, whatever, as like we're going to create the next most amazing tool.

00:51:33:15 - 00:51:57:06
Robbie
Like remember like when ever. Like when like the App Store from Apple and Android came out, right? Everybody's making the stupidest apps ever because they're like, there's a buck to be made. And I think that some people are treating vibe coding a little bit like that. And I think what you said, you said in a roundabout way is that like it's this identification of a real world problem that doesn't necessarily have to be the biggest, biggest deal in the world.

00:51:57:06 - 00:52:16:18
Robbie
Like you're not. Yeah. You're not solving cold fusion here. You're solving a small workflow thing. And I'll give you a personal example. Recently I've been on a string of a bunch of feature length projects, and those projects have just a ton of deliverables, right? Like, you know, ten different versions of the ProRes. There's five multiple DCP versions.

00:52:16:20 - 00:52:40:15
Robbie
And I found myself creating these, like sort of like drive inventory PDFs to like explain to the clients, okay, this is what's in this folder. This is the best use of this. This is what's in this folder. Here's the thing. And I got like, I found myself, you know, sort of I had a sort of I had a pseudo template working, you know, and then I would just change the client name change, but it was like it was so tedious to do.

00:52:40:17 - 00:52:57:18
Robbie
And I was like, this is a perfect job for something like an album to, to build for me. So I had it built. I said, all I want to do is I want to prompt that. I point you to the output folder, right. And it's a standard because we use a pretty standardized, naming structure in our in our project folders.

00:52:57:20 - 00:53:28:12
Robbie
Here is the here's the basic definition of each one of these folders. I want you to take a screenshot like of each one of these. These folders, insert it into PDF with the description with the file name, and make a PDF for me that I can put on the drive I saw have look. I still look it over, but it made, you know, 45 minutes into work, into five minutes of work and all I have to literally do is pointed to the source folder, and it makes this drive inventory with nice formatting, nice pictures.

00:53:28:12 - 00:53:31:18
Robbie
And I just hand that off to the client and I'm done. Right.

00:53:31:18 - 00:53:42:19
Joey
And that's not really that's a compelling use case that we haven't had before, which is, hey, I want a computer to do something for me, but a program for it doesn't exist.

00:53:42:21 - 00:53:43:05
Robbie
Right.

00:53:43:05 - 00:54:11:15
Joey
And really, it's a one off, right? I don't need to write a app or a website or a whatever that does. I don't need a dedicated app for this one. Producers emails, right? Yes. But for this project, do I want to go through a thousand of them? No. You know, it kind of bridges the gap between fully baked, done, tested, marketable software products and base level.

00:54:11:20 - 00:54:14:07
Joey
I need to get this task done.

00:54:14:09 - 00:54:32:16
Robbie
So that's a workflow one. But I'll give you a creative one too, right? So one of the as I started off this conversation by saying that I, you know, people at conferences were coming up to me and saying, I'm writing out for this and that. I think, you know, in the past decade or so, we've seen this cottage industry of, dkl plug in type folks, you know, just pop up, right?

00:54:32:16 - 00:54:54:10
Robbie
Everybody in their mom has. It used to be lots. Now it's like, I'm guessing at some point in the future, maybe it will be more, you know, effects. But that's infinitely more complicated with, GPU tie ins and stuff like that. But anyway, I got like, sort of pseudo jealous for a while of like, that doesn't say pseudo super is the right word, super jealous of a while of all these people I knew would be like making these.

00:54:54:10 - 00:55:10:14
Robbie
And I'm like, why did you learn that? Like and some people were just good at learning it, right? Like, I know you picked up DTL pretty easily because of your previous programing experience and like you were able to Gronk real quick like, oh, this is just the syntax and I like and look at these things. I'm like, right.

00:55:10:16 - 00:55:39:11
Robbie
So perfect. Need a verb coding. Right? I was doing a project maybe about two weeks ago or three weeks ago. Where have you ever been watching especially like on TNT or one of those kind of networks that's always showing movies on, like a Saturday afternoon where, like, at the end of the movie, instead of doing the full the full, frame credits scroll, the image kind of just like bounces up to the bottom and there's like a big black bar at the bottom where like, it just flows, the, flows the credits I created.

00:55:39:12 - 00:56:10:00
Robbie
I needed to do that the other day, and I was like, this is manual. I had to do it like four times, and this is stupid. Why am I doing this? So I just wrote a DCT out and this is the stupidest ducktail ever in history of DuckTales. It literally just put a black bar on the bottom of the screen where I now had this bounded area where I could just put the credits on the bottom right, but it saved me like 5 or 6 steps in resolve finding that generator, putting it in, sizing it, or maybe I saved a preset or whatever.

00:56:10:05 - 00:56:21:23
Robbie
Like I just had this area now that I could just scroll text on and it was and like, stupid, right? One off, as you said. But the ability to do those things quickly, I'm like, and who cares if I never use it again?

00:56:22:01 - 00:56:24:10
Joey
Yeah, exactly. It can go in the trash when you're done.

00:56:24:12 - 00:56:44:12
Robbie
I put very little thought into it, but I was able to explain it well enough for it to work, and it worked. Right. And so, you know, your level of sophistication with these things. My point is, is it doesn't have to be the coolest, world changing thing ever. Think about small problems and how more efficient you could be if you solve the small problems.

00:56:44:12 - 00:56:57:15
Robbie
And I think that's where really where honestly where vibe coding can step in for a lot of us is these small problems to fix. Not the huge ones, the small ones and workflow things. Yeah, I think you can definitely prove things.

00:56:57:16 - 00:57:15:22
Joey
Yeah, absolutely. You know, it's one of those like like I kind of started with, I consider it the highest level programing language. It's an easy way to tell the computer what to do. And the real knowledge is in you being able to conceptualize what you want to do.

00:57:16:00 - 00:57:39:14
Robbie
Yeah. And I mean, so I just want to be wrap this up by saying that this is its own sort of industry now. Right. As people have sort of become to see this. And as we talked about at the top, these models work depending on how well you train them. Right? And so obviously some of the big players that I ChatGPT, you know, those are, you know, Gemini, those are some of the big players from the big players.

00:57:39:14 - 00:58:08:15
Robbie
Right. But there's a lot of other smaller platforms. Some of the ones that come to mind are like lovable, versatile bolts. I'm trying to think of the other ones. I think it's Replit or Replit. These are different, platforms that are, you know, L.A based but have specific levels of training for them. Right? So, like, you know, if you're trying to do, like a full, you know, full stack kind of thing, you know, web deployment for an app, right?

00:58:08:18 - 00:58:27:20
Robbie
Like, you might go to something like, replit. Right. Or if you're trying to do something like a portfolio site, you might go to another one of these platforms. The different vibe coding platforms kind of specialize in different things. So I would just say if you feel like you're not kind of getting that the results that you want with one of the major platforms, check out some of these more specific things.

00:58:27:22 - 00:59:03:10
Robbie
The other thing I would put out there too is that while a lot of these platforms can do this coding stuff, there's some quality of life things that the, more code specific platforms can do for you. GitHub integration, for example, dealing with, you know, different versioning of deployments, feature requests, things of that nature, like I've gotten really frustrated very quickly by like the base level, ChatGPT squad kind of thing where it's like, you made me a version, I asked for a change, and then you married that back up with an old version, like, why did you do that?

00:59:03:10 - 00:59:27:23
Robbie
Right? And like in that part party got frustrated real quick. And then I made I was like, now I'm in the process of like setting up a GitHub so I can get, you know, better integrated with deployment and stuff like that. So there are different tools out there for, for different things. And I think one of the other things that you'll find in this process is that you can be really more cost efficient once you get a better handle on how these different platforms work.

00:59:28:01 - 00:59:48:18
Robbie
So in other words, you might be able to use something like Claude as your your central platform, but then you're using some of these other platforms as, as you said earlier, Joe, like sort of module agents. Right. They are really good at doing this one kind of thing. That doesn't mean that you can't combine all of them together, and it seems like you might be spending more money that way.

00:59:48:19 - 01:00:08:23
Robbie
You might not actually you might end up being more cost efficient. And how you do this by getting things to focus on different areas too. Yeah. Very cool. All right. Well, that's a 90,000ft view of vibe coding. Actually, in a couple weeks, we're going to be really excited to have on, a new sponsor of ours, the guys at Conformer Tools.

01:00:08:23 - 01:00:30:22
Robbie
And actually, Brandon Thomas, the one of the principals there. I've had these conversations with him a bunch because, he was he kind of caught me on to some of this, like, you know, vibe coding stuff. And gosh, man, when we have those guys on and things are going to be really impressed with the things that they've done with, image detection and image manipulation and all sorts of wild things.

01:00:31:04 - 01:00:53:03
Robbie
About 10,000 steps beyond what is, more complicated, some of the things that we're talking about. So stay tuned for that. Just as a reminder, you can head over to the offset podcast.com for a full library of shows. This is our 51st show, so it'll take you a while to get through the previous 50 if you're new, new to the show, but wherever you find the show, please do us a favor and, like and subscribe every like and subscribe goes a long way.

01:00:53:05 - 01:01:12:10
Robbie
And, we'd love if you consider to buy us a cup of virtual coffee here at the link below. On screen. Every, every dollar sponsor goes directly to supporting the show, helping pay our, our overhead costs, our editor, etc. so anything that you can do there, we greatly, greatly appreciate it. And a huge thank as always to our, sponsors, Flanders scientific and conformed tools.

01:01:12:11 - 01:01:27:20
Robbie
Without you guys, we couldn't do these episodes every two weeks, so we really appreciate that. Yeah. Good stuff. Man, I, I think that this is going to be, really exciting where this goes. And I'm just, you know, I'm just along for the ride trying to figure it out as I go. But I do think for.

01:01:27:22 - 01:01:28:07
Joey
Our.

01:01:28:07 - 01:01:38:01
Robbie
Workflows, our pipelines, you know, some of the small pain points and things that we could we want to be more efficient at. Vibe coding is a perfect match for it.

01:01:38:03 - 01:01:39:17
Joey
Yeah, absolutely.

01:01:39:19 - 01:01:43:22
Robbie
Very cool. So for The Offset Podcast I'm Robbie Carman.

01:01:44:00 - 01:01:45:16
Joey
And I'm Joey D’anna Thanks for listening.