SPEAKER_01 0:00

Welcome to the third episode of Old School New Tech. How are you doing? All good on my side. How about you? Feeling ready to dig into the cockroach of interfaces?

SPEAKER_00 0:11

Yes, I'm uh a bit still wild up about the audio settings that crashed a minute before starting. But anyway, let's uh let's get uh down to today's episode. I was thinking of um uh spicing things up and maybe shuffling things around and have you be the main host and you lead the way, ask questions, um basically it's it's your show today. Take it away.

SPEAKER_01 0:40

Let's do this. Welcome to old school new tech, episode three. Let's kick off with the central claim. The terminal is the cockroach of interfaces, the thing that never dies. But we're not letting it rest on nostalgia. Why does the terminal keep winning structurally, not just sentimentally? And what's the real implication when we hand a shell to an AI? Ran, I'm going to push you. Let's see if the terminal really earns its keep for someone who's not you. First question: is the terminal really the best tool for everyone, or is this just about power users?

SPEAKER_00 1:16

Alright, so this takes me back 30 odd years ago. Okay, when I started uh using computers and was just uh learning, it was um we didn't call it the CLI, we just called it the terminal uh or the computer. There wasn't any other thing to uh to use. And uh actually the the name terminal came from end computers, kind of the edge computers being uh in everyone's home, uh being just a client or a terminal that hooks up to the mainframe. But yeah, so the that blinking cursor in the terminal is or was the computer, and I found it very funny that kind of we went full circle, it was an effort of decades to kind of steer away from uh from the CLI. CLI for the non-techies here is command-lined interface. Okay, so it's a command-line interface, that's uh the acronym. But yeah, the the goal for decades was let's try to get away from CLI, and uh there was no um uh GUI uh when as I mentioned when I started, and then things started happening. But what happened is that uh the power users, as you called them.

SPEAKER_01 2:37

Exactly.

SPEAKER_00 2:38

One second, one second. I think go ahead. All right, I wasn't streaming. Uh never mind. Uh we'll just keep that recorded and I'll and I'll uh upload it later. So, yeah, so what happened is that the um power users kept using CLI because they found it to be faster, more equipped with what they need to do. It has amazing capabilities, and um they're the one that that kept on using it. And we saw in the AI space the same process of what I've been through, only backwards. So they started with with a web chat interface, or with ChatGPT was introduced, or started with the web chat interface, and then it um uh they uh introduced an API, which internally they probably always had. Uh, and then the first kind of interface uh that the public got access to was uh the CLI uh with tools like Cloth Code. Uh and only then came the desktop applications. And I think there's a reason, is because those power users and those companies are uh were using and I assume still use the CLI as their main interface, and that's the tools that they built from this for themselves, and hence uh the first tool, the first interface that they've used. So uh to to sum up kind of the the first act, I would say that despite 30 years or 40 years of uh efforts to stay clear and kind of get over the CLI, it is like the cockroach uh after a nuclear attack, it is cockroaches uh of interfaces, and um it just still is around. And I would like to hear your thoughts about why you think that is, what's so powerful about the CLI, and why did all the um AI labs went through that same route of uh and even before the AI labs, companies like Stripe, etc., they all went through the same route of let's uh give you a web interface and then straight to the CLI.

SPEAKER_01 4:48

Spot on. And here's the structural reason. The CLI survives because it's the lowest level, most direct interface to the machine. And that's exactly why those AI labs followed the same pattern. The web chat is the demo layer, but the moment you want real power user control, you drop down to the command line. It's not nostalgia, it's composability. Small tools, piping outputs to inputs, direct access to logs, no abstraction in between.

SPEAKER_00 5:15

So you mentioned uh pipe. Can you kind of uh give uh a bit of uh information about what are pipes and the terminal to those who are not used to living in the terminal like uh l like senior devs and just explain what's so powerful about that?

SPEAKER_01 5:34

Absolutely. Pipes are a way to take the output of one command and feed it directly as the input to another command. It's like chaining tools together in a sequence, each doing one specialized job. For example, you might list some files, then filter that list, and then count the results, all in one line. It's powerful because it's modular. You're not locked into one monolithic program. You're composing simple, flexible commands into something more powerful. And that's the essence of the terminal strength.

SPEAKER_00 6:04

Right. And it's funny that you mention that because you know a few years back, I ran uh an algorithmic trading company uh or startup, and um we we used to deal with lots of uh market data, which comes in buttloads, right? So we had to deal with tick-level data, which is microsecond-level data of every single trade and every single order that happened, and then from that we had to aggregate it to uh second level and minute-level data and kind of derived uh what people used to um are more familiar with, kind of the minute-level candles and uh uh hourly candles and so forth. And um, no matter what we did, um we and we used powerful tools like um Kafka for ingesting in Click House as the database and a few layers of caching and everything. So we did everything that we could, but nothing for processing that data uh once we had it and converted in the, as I mentioned, to higher uh level uh or higher frequency type of uh candles, nothing was faster than manipulate the those CSV files through the terminal. It was one command to chunk them, to uh move them between uh servers, aggregate the data. It was all extremely fast, uh, much faster than writing things in Python, Go, and even C. Yeah, that it is that powerful. And I think that's why a lot of uh developers kind of tend to uh lean into it, and that's what we're seeing.

SPEAKER_01 7:47

Exactly. And that speed and flexibility are why the terminal isn't just sticking around, it's thriving in the AI era. It's not about being old school, it's about having a direct, composable interface. You didn't need a GUI or a heavyweight script when a single pipeline of shell commands could transform massive data instantly. That's the underlying architecture advantage. It's not sentimental, it's structural.

SPEAKER_00 8:11

But having X access to logs and have being able to manipulate files and have direct control over the uh computer itself, uh maybe not the UI of the computer for that, you need a different layer. But having all that access is what makes uh AI coding agents and AI agents in general be so powerful in the terminal. And you have to understand that every time a company introduces something like the Claude Desktop or Codex, they're running a lot of the um core loops and tools and manipulations on a shell that you just don't see on the CLI that you don't see. Um they're still running it over there, and then they generate the output uh with artifacts and all of that stuff. Uh, that's just the output presented nicely to you. But even the images and even the graph the diagrams and graphs and whatever it may be is still being generated on the CLI level. So these are really just in most cases, I'm not saying in all cases, some cases are truly unique to the GUI, but in most cases, they're are trying to put a nice face on a uh a not so inviting interface in order to appeal to the broader market. Would you agree with that assumption?

SPEAKER_01 9:40

Absolutely. That nice face is for the mass market, but the core of the operation is still that raw, powerful command line logic underneath. That's why they ship the CLI to the power users first. The terminal is where the real machine control happens, even if the final product looks polished and friendly.

SPEAKER_00 9:59

Now, my whole kind of thesis for this um for this uh episode today was that I think that even the non-developers and the non-tech and even the C-suite should get comfortable with the CLI just because it gives them a lot more power. And maybe you can come up with uh a few reasons for them. What do you think that is? First, uh the why why do you think they should uh jump on the CLI? Maybe not for all of their work, but for some of it. And what do you think the benefits will be on the in the long term compared to s just doing things faster now? What do you think they'll gain in the longer term uh using the CLI?

SPEAKER_01 10:47

Long term, they gain true understanding of what the system is doing. It's not just speed, it's visibility. They can inspect logs, track down issues, and supervise agents directly. They'll rely less on intermediaries. And as agents automate more tasks, having that supervisory layer at the CLI level means they stay in control. That's the real long-term benefit.

SPEAKER_00 11:09

I've also noticed that the people who uh dig into the CLI, even if it's just to use uh clawed code or a list of directory, let's let's keep it basic. Okay, that let's consider that's all they're doing. They are still less intimidated by the computer that the more time goes by because they've they've seen how it works. It's like opening the hood of uh of a car. When you open up uh a Tesla, you you see nothing there. I'm not saying it's a bad car, it's an excellent car, but the experience and what you learned on how it works is just non-existent. Uh, but if you are gonna pop up the hood of an older car, you're gonna see exactly how the engine is built, and you you're gonna see the wires going into the battery and all the pipes and the cooling, and you'll understand more. And um a mechanic, uh friend of mine, uh maybe 10 years ago, complained on how the the fact that uh every car is a computer now just makes their lives a whole lot easier. It used to take them 30 minutes to fix a minor issue, and now they have to take apart half of the car just to change a pipe that costs 10 bucks. Um you end up with a $500 bill just because of the amount of work they had to put in. So it's it's kind of the same analogy uh with uh with I think the CLI, you get closer to how things actually work, which makes you more confident in what you're doing in the outputs of the the um of the software that you're using and in your own abilities. I think it it uh leans a lot into uh into uh building that sense of agency.

SPEAKER_01 13:00

Exactly. And that sense of agency is key. When you interact at the CLI level, you're right at the layer where the machine responds instantly to your commands. You see exactly what's happening under the hood. That builds real confidence, even for non-developers. It's not just about being faster today, it's about being more capable tomorrow.

SPEAKER_00 13:20

So, how would you, if it was up to you and you had to create like a getting started guide with the CLI for uh the C-suite or their the non-technical founder, someone who uh runs a flower shop or whatever it may be, uh they still need to use AI tools uh uh that are a bit more than opening up Chat GPT. So, what would you recommend as uh kind of as a quick roadmap of getting familiar with CLI? Because after that I want to discuss about some of the dangers uh that comes from that same power. Great plan.

SPEAKER_01 14:02

The quick roadmap for an get comfortable with simple commands.

SPEAKER_00 14:07

You got cut off there. Can you restart uh that last sentence?

SPEAKER_01 14:12

Of course. From there, you can go deeper step by step, gradually building more comfort and capability. So give us those step by steps. Alright, let's break it down. Step one, open the terminal and run a command like ls to list files. Step two, change directories with CD and navigate around. Step three, open a file with cat or less to peek inside. Step four, try a simple pipe, like listing files and filtering with grep. And step five, run a small AI-related command, something that triggers an automated task. That builds a foundation.

SPEAKER_00 14:50

I would probably ask if we're talking about uh um AI, obviously, I would probably fire up something like fall code and in the terminal and just tell it to um teach me how to navigate this thing. Show me what to do, where to do it, let's do it uh together, and um have it be your hands-on tutor. I think you're gonna gain a lot of uh a lot of value from working that way.

SPEAKER_01 15:22

Spot on. Using an AI assistant right inside the terminal as your guide gives you that extra confidence. You're learning by doing, and the agent can walk you through each step. That's a brilliant way for a non-technical user to get familiar quickly.

SPEAKER_00 15:36

All right. So we mentioned that uh and we talked about how uh the CLI gets you a lot closer to the ground, a lot closer to how the machine actually works. But that also comes with, you know, as a uh famous saying says, with the great power comes great responsibilities. That same power abilities that you have on your computer can also be uh destructive. So what are some of the things that you probably have to be aware of?

SPEAKER_01 16:09

One major thing is the absence of guardrails. The command line runs exactly what you tell it. No are you sure prompts. A single mistyped command can delete critical files or bring down a system. So always double check destructive commands and know that the power and the danger are two sides of the same coin.

SPEAKER_00 16:28

I would add never type in a command you uh found on the internet without fully understanding it, uh, and maybe uh consulting your uh AI about it. Uh because you're gonna find a lot of uh people online recommending that you're gonna run something like uh RMRF. This is basically RM is remove, and RF is uh to do it recursively, and F means to do it forcefully. So there's no confirmation dialogue, there's nothing coming in. You're just going to delete your entire operating system and your entire drive. Uh with really no, there's no recycling bin uh in the in the terminals. So don't and people just sharing this as a gag, like like it's funny, it's uh a harmless prank, but uh you do not want to just copy and paste commands you found somewhere without fully understanding what they're what there are.

SPEAKER_01 17:24

Absolutely. It's crucial to slow down and understand each command. An AI tutor can help explain what a command does before you run it. That way you stay in control and avoid unnecessary disasters.

SPEAKER_00 17:37

All right, so let's um let's summarize because on the next uh uh episode I would like to talk more about how to enable more agency in this day and age and why you um why you even as a non-techie, and I know that usually I talk to the tech crowd, but I think that it's also important to bring the non-tech people, the non-developers into that into that mix. And I think that you know, uh if we have to separate, I think that the UI is where you look at the work that you've produced. It's a lot pleasant, uh much more pleasant to look at files on the UI and read documents in the UI, uh, on the GUI, I mean, and uh do things that you can't even do on the terminal, like looking at graphic files. But I think that terminal is where the actual work happens, and specifically work that uh is uh uh data driven. And um even though we kind of spent the past few decades now trying to hide the machine in a nice interface and uh making it all nice and pretty with nice buttons and layout. Well, this is great, but every time, especially developers and engineers, um whenever we needed to do some serious work, we immediately fire up the terminal. And I think that uh the reason is I don't think that the CLI is surviving despite of an I. I think that prop possibly AI is the best argument for getting into using the terminal if you haven't already. Uh, and I think that uh gives you a lot more control and a lot more power uh into getting the job you really are trying to do. Like I work with the Claude Desktop and I work with uh Claude uh co-work, whatever it's called, and I work with the terminal on different tasks, and obviously, because sometimes it's just more convenient to look at files and read documents on the GUI. But whenever it needs to um access uh files on my system, it goes through this whole drama of let me check if I have a file uh system MCP and let me check if I can do that and if the file is readable. And um I I I I don't I I don't have time for this. I just want to uh uh get down to um to having it do the work. So whenever I need to actually do something that's outside of a pure chat, uh I'm on the terminal. And and the the other it goes also the other way. If I only need to do a ch all I'm doing is a chat and I don't need to kind of for let's say for brainstorming and I don't need to access any file or do any work, I'll prefer the chat interface. The I'll prefer the GUI. But it's really depends on what I'm trying to achieve.

SPEAKER_01 20:41

Exactly. It's all about the task. The GUI is where you reflect on the output, the terminal is where you get the heavy lifting done, especially when you need that direct machine control. And AI makes Batterminal even more powerful.

SPEAKER_00 20:55

Alright. So I think that's it for today. Do you have any final words you want to close up? I mean, uh you're the host. I think you could be a bit more verbose next time when you're a host, uh, but you've done a pretty good job. So are there any last words uh that you wanna take us out with?

SPEAKER_01 21:14

Fair point. I'll lean in more next time. One last thought. The terminal isn't just for the tech crowd anymore, it's the place where human agency and AI capability meet. And next time, we'll dig into how to wield that power wisely.

SPEAKER_00 21:28

Alright. So thank you everyone who uh joined us and listened to this episode. I did not stream this one because of the uh issues that I've had with the uh AV setup here, but this episode still goes on the um on the YouTube channel and still goes on the uh X uh account, so feel free to comment, like, subscribe, you know, this whole shebang thing. And uh we'll see you next time, hopefully live. Cheers.

SPEAKER_01 22:00

Cheers everyone. Looking forward to next time, live and uninterrupted.