This is a great example of how silly this whole thing is. There’s next to nothing to these claws. Turns out that if you give an llm the ability to call APIs they will.

Depends on the car wash. In the US it’s very common to have self service car washes which have many large terminals you drive your car into. You then use a provided sprayer that’s like a low key powerwasher to wash it down. Many people bring sponges/rags to use as well.

To call something AI it’s very reasonable to assume it’ll be actually intelligent and respond to trick questions successfully by either getting that it’s a joke/trick or by clarifying.

The issues with such tools are highly documented though. If you’re going to use a tool with known issues you’d better do your best to cover for them.

Which interestingly is the meat of this article. The key points aren’t that “vibe coding is bad” but that the design and experience of these tools is actively blinding and seductive in a way that impairs ability to judge effectiveness.

Basically, instead of developers developing, they've been half-elevated to the management class where they manage really dumb but really fast interns (LLM's).

But they dont get the management pay, and they are 100% responsible for the LLMs under them. Whereas real managers get paid more and can lay blame and fire people under them.

Maybe it’s just the people I’m around but assuming you write good tests is a big assumption. It’s very easy to just test what you know works. It’s the human version of context collapse, becoming myopic around just what you’re doing in the moment, so I’d expect LLMs to suffer from it as well.

> the human version of context collapse, becoming myopic around just what you’re doing in the moment

The setups I've seen use subagents to handle coding and review, separately from each other and from the "parent" agent which is tasked with implementing the thing. The parent agent just hands a task off to a coding agent whose only purpose is to do the task, the review agent reviews and goes back and forth with the coding agent until the review agent is satisfied. Coding agents don't seem likely to suffer from this particular failure mode.

There’s a ton of semantic drop in css libraries similar to this. Love seeing new ones. Quality varies wildly but this site shows 50+ drop in stylesheets for those writing semantic html: https://dohliam.github.io/dropin-minimal-css/

I had to read your comment three times before figuring out that you mean “drop-in”. Sometimes hyphens do matter! :)

This isn't upvoted enough. This is more interesting than the OP's project! Thanks for sharing!

I love it. You can use the right arrow to cycle through them.

do you have any recommendations from the list?

Here’s some that seem genuinely useful to me depending on what you’re looking for.

- https://concrete.style/

- water.css https://watercss.kognise.dev/

- magick.css https://css.winterveil.net/

- mui.css: https://www.muicss.com/

- pico.css: https://picocss.com/

It would be foolish to believe this isn’t happening basically everywhere. The reason this is news right now is because Amazon got cocky enough to buy an ad spot on the most watched TV event in the US showing the extent of their surveillance network.

here in my town in Spain I still see no cams, just phones and you cannot publish without consent when filmed in a public venue.

The people I know that use them the most also seem the most likely to buy into hype. The coworker who no longer answers questions by talking about code but instead by talking about which skills are the best is the same who posts all the hype.

The use of the word Tragedy in the name I think makes it easier for people to excuse themselves when they monopolize the commons. “Oh it’s a tragedy humans are just selfish we can’t avoid it.” The tragedy is that people are comfortable excusing others selfish, greedy behavior by saying it’s innate.