simonkagedal

Isn’t that exactly what exploring is?

Why not?

I don’t find this pedantic at all, I just find the language used in the article to be genuinely confusing.

Taken down from YouTube now, it seems... anyone have an alternative link?

So are you saying that if they were intelligent agents rather than word generators, they wouldn’t make mistakes like “send a message to the wrong (similarly named) group”? Are humans intelligent agents?

It’s good to inform people that this hack exists and can work for some situations, but no, that’s not “having comments”. Not even close.

What state management solution(s) do you prefer?

They should be toggles! Every now and then I will press the wrong button and will have to wait for the elevator to stop, open doors, close doors at a floor no one wants off on.

I mean, I haven’t done the usability research, probably there are some good reasons for it’s not a good idea to just make them toggles, but I would find it neat.

Sounds a bit like the idea behind shadcn/ui. You start from the generated components, but the idea is to fork the code.

(Then they seem to also have added their own kind of dependency management thing to update components, which seems to me to kind of defeat the purpose..)

There are lots of good use cases for vibe coding (”never reading the code”), prototypes, various explorations and one-offs. I’ve done various kinds of migrations where I didn’t bother to review the code much, just the output.

Possibly also some user-facing tools with a limited task and runtime environment.

Incidentally, these are all use cases where performance isn’t critical, typically, so you might as well write them in Python or Typescript or whatever makes most sense for the task.

Real production code? Yeah, you still need to be able to read it and understand it.

But people claim that text is AI-written on the most ridiculous grounds, like using proper typography. You might be missing out on interesting stuff!

Same. Meanwhile, I _read_ more code than I ever have.

Furthermore, for the example given, it would have made a lot of sense to me to generate those article summaries on the backend. Once and for all, no need to burden each client device (which are going to need to download the content anyway), no need to tie yourself to a specific provider (Apple in this case), can have the same experience everywhere. Of course, the backend could use a local (to itself) model.

Not saying it’s _wrong_ either – maybe it doesn’t use a backend of its own (the client downloads content directly from some predefined set of sites), maybe there is functionality to adjust how the summaries work that benefit from doing it on device, etc. Just doesn’t convince me that ”local AI should be the norm”.

I would say yes, there’s a difference, in general. I would much rather leave the unsafe code to crates used and tested by many other applications, than have them in the application code itself.