Slopfluencer

The (coding) vibes have shifted

Written by Patrick by hand

Guest writers

Its 2026 and the coding vibes have definitely shifted

As I wrote in Its Time To Let The Model Drive, the latest generation of models have hit some invisible line where they went from "meh, they're okay" to "holy crap they're really good". Over the break you could see this unfolding as bored devs off from work finally decided to check out what all the buzz was about and use these models to build stuff.

If you go on twitter, the vibes have definitely shifted. People are completely shocked at how good they've gotten. Particularly Opus 4.5 and GPT 5.2 Codex have been blowing minds.


Its caused quite the divide in the developer community with some on the vibe coding bandwagon, some begrudgingly starting to acknowledge that this is the future, and some staunchly against it.

But its pretty clear that vibe coding is here to stay and that coding agents are a force multiplier.

Joining the flock

Over the break I too joined the flock of developers working on side projects. I spent $500 in subscriptions and API credits building Familiar Fleet. I averaged 5-6 hours a sleep per night, the rest of the time was spent managing multiple agents building out various features in Fleet. It's been a long time since I've felt this compulsion to build something, and I haven't had this much fun in a long time.


I maxed out a $200 Cursor Ultra plan in 1 week pushing out 2.2B tokens.

I went into this project with only 1 rule. This is going to be a fully vibe coded app. I would not write any code.

So far, it's been working pretty well.

Fleet is a desktop app built with Rust (Tauri) + Typescript + Tailwind + Golang (backend). Its an agent orchestration system meant for non-developers and provides a nice interface to spin up agents. I'm actually not sure who its for, but I think the agent paradigm is very powerful and I think non-developers can get a lot of value from it, so I want to put this into the world.

Product Development

I went into building fleet with a really basic idea. "Claude code for normies". The hardest part about building something so vague is that you have no idea what works. What does it even mean? What do normal people even want? Are agents even useful to non-developers? Who are the people that would benefit from it?

The thing I really love about vibe coding is that it gives you the ability to iterate on the product very quickly. You can change something within minutes that might have taken me hours or days in the past to code. The ability to touch, feel, and interact with the thing I'm building makes all the difference when exploring a new space.

This is an important distinction that people online keep missing and arguing past each other about.

If your priority is to build stable, high quality systems, you probably don't want to hands-off vibe code your application.

However, if you're working on a startup that doesn't have product market fit, the ability to vibe code something and get it in front of people very quickly means that you get that many more chances to refine your ideas and build something that fits user's needs. It also means you get many more chances to get it right before you run out of resources.

Where do we go from here?

Ultimately, there is going to be more software in the world. Some will be good, some will be bad. The barrier to entry to develop is lower than ever. That's probably a good thing, as more people will be able to build and produce value. It also means change in the world, and in our industry. It's just a fact of life.