Some of these are genuinely nice. I really like the action slide-out, the wall reveal, and the slide-off reveal.
Unfortunately for a thing whose core job is polished UI, there's still quite a lot of polish needed before I would be willing to implement any of this in my UI
To name a few :
- the swap icon state theme preview switcher cascades the element brightness rather than fading them together.
- The confirm reveal has something wrong with the spring every third or fourth click, which is strange
- Cards: the stacked deck cycle. When you click Next, it doesn't draw the top card.
- The shared element expand option: when you minimize, the spring dampening pushes the components outside of the container.
- Swipe to dismiss causes the container to temporarily show a scroll bar.
100% agreed. Although its less about writing it and more about holding it in your mind. Think what you may of vibe coding it's very hard to justify rolling every line by hand when modern LLMs can produce pretty reasonable code at scale.
Coding is however just one small aspect of bringing software into being. We generally start with an intuition. That intuition comes from context.
That context, hard won as it is, for software engineers at least, was mostly a side effect.
You had to buffer a significant portion of the system in your mind to be able to manipulate it. LLMs remove that constraint. Now you can just prompt from the upstream intuition and its passable a good portion of the time.
Notice the catch? If you don't get to the beat of the system your interaction with it will be jarring, for yourself, for the person using the software and for the agent building it.
So I made a tool to help get the context into my head faster. No its not an app (it could be but meh) Its a skill that helps the LLM make a voice narrated walkthrough of the complexity so you retain context
Check a demo here if you want https://theronburger.github.io/review-story/
Am I the only one thinking just blurring the site is a little naive? It's relatively trivial to extrapolate the centers of the blobs from a blur. Pretty strange thing picking up a ticket to obfuscate your company's data centers on the map to protect them against drone attacks and then kind of just phoning it in
Probably phoned it in because they know the ukranians can just not use yandex maps to bomb russia. But hey, boss gives you a dumb easy job you don't argue.
Haha yeah and I’ve been building one for myself as a side project. I think there are many people experimenting in this space. Going to be interesting to see how it develops.
It's not the first time we are encountering this issue. We've seen it in other autonomous systems. Trains are an older one, cars are a newer one.
As you move out of the lower levels, the operator has a tendency to assume the system is increasingly more capable than it is. In trains, its so bad that they generate fake signals that the operator needs to respond to within a timeframe. I'd love to see this with implementations of other critical autonomous systems like this. Occasionally inject known errors into the system and expect the operator to catch them. If they don't, well... If it was a train driver I think we would fire them. If its an intelligence operative ordering a strike? :shrugs wearliy:
note the airline industry has moved past firing pilots who make mistakes, since that turned out to be a recipe for more plane crashes, not less. Instead, they find out why the mistake happened, and fix it. In some cases, this involves firing the pilot. They do not do that by default.
U.K. railway like this. Root cause analysis. Sometimes the train driver is at fault, but usually there’s a way the problem could be caught or prevented.
I do this for porting things to DOS. Was swapping a CF card back and forth between a 486 PC and my laptop that was running Claude and it was extremely tedious and required me to physically be at the system.
Automated it entirely by giving Claude hands/eyes/ears so it can take complete control of the 486 using a raspberrypi 5, a usb4vc HAT for PS/2 and a VGA capture device. Adding an ethernet card and a tcp/ip boot profile for FTP, Claude then can update binaries, test them, and gather logs. Now I just steer Claude and it handles interfacing with the machine for me.
I had no idea KVMs existed until an agent filled me in last night (I had the idea of building one with an fpga so an agent could drive os installation). Lo and behold the next day KVMs are on the front page of Hacker News!
