The last bash from an llm

The last bash from an llm

Experiment
02/12/2025
Jonas Lindeman
Digital Designer
Vy logo
Vy logo
As the AI train ramps up speed, more and more trivial tasks are being delegated to Large Language Models (LLMs). I'm no saint in this; I use LLMs every day to speed up processes, create simple components for Framer, or get information about new software. It's efficient, but I’ve started to feel like I am losing my ability to learn things deeply.

I started thinking about this while working with media compression. In the digital landscape, we are constantly compressing images and videos to make websites faster and more accessible. I discovered FFmpeg some months ago, and I was immediately intrigued by how powerful it is.

I recently learned that FFmpeg is single-handedly the most important tool for YouTube, Instagram, TikTok, and practically every platform that handles video. It is the engine room of the modern visual web. But it's a pain to learn the ins and outs of all the "flags" required to use it.

What is FFmpeg and how is it used?
FFmpeg runs in your terminal. To use it, you write commands (scripts) to handle compressions, codec changes, or file extension swaps. There are hundreds of flags, and knowing which options go with what just to get a file that runs smoothly is difficult. For a long time, I relied on LLMs to help me write these commands, and they would look something like this:

ffmpeg -i input_video.mov -c:v libx264 -crf 23 -preset medium -pix_fmt yuv420p -movflags +faststart -c:a aac output.mp4

I would open the terminal, find the folder with the file, copy-paste the command, run it, and move on. It worked almost every time, but I can't say I really learned as much as I should have during the time I used it.

How can I learn FFmpeg easier than reading?
I'm a big "learning-by-doing" person, and reading documentation page after page is not my favorite method of learning. I decided to try to make a UI for FFmpeg that could output commands from my settings based on buttons and sliders. I wanted a live-updating command line shown at the bottom of the UI, and a "Run" button that executes the script in the terminal. I designed the base of the UI so that an LLM could help me add all the "flags" I missed later.

The result became a cheat sheet and generator that breaks down the somewhat cryptic command line flags into a human-friendly UI with buttons and sliders, grouped like this:

  • Presets

  • Essential flags

  • Optional flags

  • Advanced flags

Let's start learning FFmpeg
Just by building the UI, I've already learned a lot more about the different flags I can use to optimize my files. Through my research on what's out there regarding FFmpeg, I've started to see more niche flags that could be useful in the future. This is a first step in regaining my own learning, and a reminder to use LLMs to kickstart a process, not just to generate the final result.

And maybe that’s the real point
AI doesn’t remove the need to learn – it removes the friction between curiosity and action. If I use it just to ship a command, I lose something. But if I use it to build the thing I wish I had, I learn ten times more. FFmpeg just happened to be my example. The deeper insight is this: Use AI to accelerate doing — not to bypass learning. Because once you start making again, the understanding comes back. And with it, the joy of knowing not just what something does, but why.

Vy logo
Vy logo
Thoughts from Ebb

More Thoughts

More Thoughts

Article

The fourth industrial logic

Thought. How we think. Rethinking. Thinking things through. “I’m thinking of you.” We invoke thought far more often than we realise. We try to keep a sober distance from it.
“You are not your thoughts.” Yet we constantly soften feeling and opinion by replacing them with the gentler “I’m thinking that…”. As if thought were a fragile seed of opinion — delicate, unfinished. Always hovering just beyond certainty.

Article
The fourth industrial logic
Thought. How we think. Rethinking. Thinking things through. “I’m thinking of you.” We invoke thought far more often than we realise. We try to keep a sober distance from it.
“You are not your thoughts.” Yet we constantly soften feeling and opinion by replacing them with the gentler “I’m thinking that…”. As if thought were a fragile seed of opinion — delicate, unfinished. Always hovering just beyond certainty.
Article

Reclaim Your Imagination

The noise. That word has been around for many years. For a long time, people have tried to stand out from the noise—not drown in it. But very few succeed. And with every attempt, the noise grows louder, ironically. Today, the noise is digital, just like the rest of society. And it has been rebranded under a new name – you probably know it as Content.

Article
Reclaim Your Imagination
The noise. That word has been around for many years. For a long time, people have tried to stand out from the noise—not drown in it. But very few succeed. And with every attempt, the noise grows louder, ironically. Today, the noise is digital, just like the rest of society. And it has been rebranded under a new name – you probably know it as Content.
Article

The Death of Brand

Another generative AI tool launches. This one promises “studio-quality results.” It proudly displays how easily brands can now generate glossy, flawless imagery. Perfect humans, perfect lighting, perfect worlds — all for the price of a subscription. That’s when it hit me. That funny feeling. I’m bored.

Article
The Death of Brand
Another generative AI tool launches. This one promises “studio-quality results.” It proudly displays how easily brands can now generate glossy, flawless imagery. Perfect humans, perfect lighting, perfect worlds — all for the price of a subscription. That’s when it hit me. That funny feeling. I’m bored.
Article

Ebb. Year one.

It’s been 365 days since we blasted off to find ore in faraway place called future design. One of our first posters said it best. Abandon all ego. Because when ego steps aside, hope steps in – and what once felt hopeless becomes a place you can shape. This is what year one with Ebb has been about.

Article
Ebb. Year one.
It’s been 365 days since we blasted off to find ore in faraway place called future design. One of our first posters said it best. Abandon all ego. Because when ego steps aside, hope steps in – and what once felt hopeless becomes a place you can shape. This is what year one with Ebb has been about.
Photo from my private collection
Article

There is something about water

The way it moves, reflects, transforms — and how we’re drawn to it from the very beginning. As children, we play in it without questioning its depth or force. There seems to be an endless amount of learnings to draw from the sea, not just for what it shows us — but for what it reveals when it pulls back.

Photo from my private collection
Article
There is something about water
The way it moves, reflects, transforms — and how we’re drawn to it from the very beginning. As children, we play in it without questioning its depth or force. There seems to be an endless amount of learnings to draw from the sea, not just for what it shows us — but for what it reveals when it pulls back.
Article

Why change efforts fail and what to do about it. 

At Ebb, we love making ideas tangible. Some even make it onto our walls, just check out our Culture Pages. This is not about us being in the business of plastering feel-good slogans everywhere, empty inspiration doesn’t drive change, action does.

Article
Why change efforts fail and what to do about it. 
At Ebb, we love making ideas tangible. Some even make it onto our walls, just check out our Culture Pages. This is not about us being in the business of plastering feel-good slogans everywhere, empty inspiration doesn’t drive change, action does.
Article

You and me, we have a problem!

In the next two years we will see the equivalent of 50 years of technological progress. Why is that a problem? Because traditional strategy can not keep up with a rapidly changing world. Businesses need to evolve, but they are stuck in an old paradigm.

Article
You and me, we have a problem!
In the next two years we will see the equivalent of 50 years of technological progress. Why is that a problem? Because traditional strategy can not keep up with a rapidly changing world. Businesses need to evolve, but they are stuck in an old paradigm.