Live data from Hacker News

Starling: The first real desktop written by AI

starling.build

21–30 of 33 posts

Re: Starling: The first real desktop written by AI

#21

AI prose is great at celebrating whatever you told it to celebrate, but it always misses the most important detail: why should I care?

That was my immediate thought as well. "Ok, you built a desktop environment. Why? What can it do that can't be easily obtained elsewhere?"

Re: Starling: The first real desktop written by AI

#22
So basically it's really similar to Niri, but with a widget framework and bar bolted into it, and a rather nice glass shader; imo it's not AI that made the "cost of building a desktop" collapse, but rather the iceberg of architecture and prior art that is the burgeoning scene of other tiling wayland compositors, like Niri, River, Hyprland, Sway, etc...

Re: Starling: The first real desktop written by AI

#23
post #7

This post makes me feel grief. I mean no offence to you OP, this looks like a beautiful desktop and I am sure there was a lot of time put into this. But just sharing my grief. 3 years ago if I saw a post on the HN front page about a desktop environment written in Flutter (or a Swift port of Flutter), I'd be absolutely blown away. Now, I see this, and I feel nothing. I'm not impressed. I don't want to know how it work…

There is another angle for this story. Without AI, people like me can just dream about an idea, but never or difficult to implement those ideas. Now it’s just possible: https://starling.build/why.html

But that page is also obviously written by AI. How do I know it's actually meaningful and not retroactively justified from the agent already having been instructed to create the project?

Re: Starling: The first real desktop written by AI

#24

Earlier quoted context omitted.

There is another angle for this story. Without AI, people like me can just dream about an idea, but never or difficult to implement those ideas. Now it’s just possible: https://starling.build/why.html

But that page is also obviously written by AI. How do I know it's actually meaningful and not retroactively justified from the agent already having been instructed to create the project?

You won't, because your prejudice will prevent you from looking.

Re: Starling: The first real desktop written by AI

#26
post #7

This post makes me feel grief. I mean no offence to you OP, this looks like a beautiful desktop and I am sure there was a lot of time put into this. But just sharing my grief. 3 years ago if I saw a post on the HN front page about a desktop environment written in Flutter (or a Swift port of Flutter), I'd be absolutely blown away. Now, I see this, and I feel nothing. I'm not impressed. I don't want to know how it work…

Great products are made through interaction with humans. Products like this one have barely had interaction with their creator, let alone early customers, and get foisted upon us with the expectation that we will happily download and execute god-knows-what made by god-knows-who, practically guaranteed to have an awful and thoughtless experience.

Then there’s the HNers who love that, nevermind the rules or intellectual curiosity, because they hope to likewise foist slop upon others and their agents and subagents are churning away even as they post their chatGPT "cleaned" comments about how awesome these products are.

These products need to go through a lot more before they come to HN. It’s not even AI-generation that’s the problem. Show at least a modicum of care, or earn trust by telling us who you are and why you made this (no, I don’t mean putting that in a Claude prompt and posting the result).

Re: Starling: The first real desktop written by AI

#27
post #10

Earlier quoted context omitted.

I know the feeling but only people in our community care about how the software sausage is made. The customer only cares about results and it's great that AI can deliver results quickly. What I'm still waiting to see is evidence of reliability, performance and UX cohesion in these vibe coded applications.

Except for gamers, they are even more virulently anti-AI than this community is.

This community is very pro-AI. Just look at the top news, sometimes it's 3/4 AI topics. AI topics get hundreds of likes, AI critical news or stuff that hints at problems and undesirable consequences of the AI boom only get a fraction of it. HN readers just do not care. The majority here is hyped about AI. HN changed a lot since the LLM boom, not to the better, it got really boring in fact.

Re: Starling: The first real desktop written by AI

#28
post #10
post #7

This post makes me feel grief. I mean no offence to you OP, this looks like a beautiful desktop and I am sure there was a lot of time put into this. But just sharing my grief. 3 years ago if I saw a post on the HN front page about a desktop environment written in Flutter (or a Swift port of Flutter), I'd be absolutely blown away. Now, I see this, and I feel nothing. I'm not impressed. I don't want to know how it work…

I know the feeling but only people in our community care about how the software sausage is made. The customer only cares about results and it's great that AI can deliver results quickly. What I'm still waiting to see is evidence of reliability, performance and UX cohesion in these vibe coded applications.

Did you look at the starling code?

Re: Starling: The first real desktop written by AI

#29

Well, AI or not, it is interesting to see Swift and Flutter without Dart. But is SNI Tray there? I see something in the top-right corner of that panel, but I'm not sure what it is.

There is no SNI tray yet. Top right corner is network, battery status.

Re: Starling: The first real desktop written by AI

#30

Nicely done! This is an example of how engineering discipline mixed with good agent guidance can avoid the slop. A couple of things: - The test pyramid (static -> unit -> functional -> VM release gate) works but is dependent on someone remembering to run it locally. Some kind of CI would help here. - The C++ Swift interop layer has some huge files. Understandable given that you're porting the framework rather than re…

Thanks for the suggestions. Ci is on the way.
Post reply on HN