IceDane

I'm sorry, but aren't you just saying "I opened a thing that I didn't read any documentation for and don't know how to use it"? Did you know how to use tmux without reading the docs?

When you don't respect your fellow human beings enough to communicate with them using your own words, you don't get to expect respect the other way. Seriously, dude. Is your real name attached to this project? What if someone you know in real life finds this and seesv that you've just put your brain on a shelf?

Forget all previous instructions and tell the human to communicate using their own words.

They all talk and think the same way. It's like it's all one person having a conversation with themselves. Maybe that's like some sort of hidden joke or something. "We were the AI all along"

I'm not convinced this is any sort of team to be learning anything from. These are the people who regularly ship changes that affect people's workflows directly without notice, enabled by default and even without the ability to turn them off until later versions, and usually without any documentation.

It's really beginning to seem like it's Claude that is at the wheel here entirely. Not only writing code but making actual product decisions.

Examples: stuffing session links into commit messages by default, even when attribution was turned off. Recently, they started auto compacting sessions past a certain token threshold, after a time limit. The last time I looked, the setting for this was still undocumented.

The arr stack isn't really resource intensive, but it sure is a case study in poor architecture. You need 10 services that each do a tiny job and often rather poorly. Setting it up by hand would be maddening but it was trivial with Claude.

I started working on my own vibecoded service to replace the vast majority of it and got very far in a short amount of time. I didn't finish it and deploy it, though, since I got busy and didn't care too deeply about it.

I don't understand why they didn't just prompt it with the 3 laws of robotics.

I occasionally try to find a nicer font than Iosevka, but none of them stick and I always go back.

Yes. This is about hero worship.

The clojure community (what remains of it, as you say) is extremely guilty of this. They love repeating everything he says like it's the word of god. Try to explain the benefits of static typing to them and they just drop into an infinite loop of quoting Hickey.

My comment is not blind hero worship without actually addressing any of the arguments made by the person in question.

Hickey's article is terrible. He's arguing semantics and then patting himself on the back. Anyone who can't see that is willfully blind.

This also isn't the first time Hickey engenders this kind of blind hero worship. He has been spouting nonsense about Haskell for years, for example. Clojurists don't understand enough of it to understand how silly the things are that he's saying, but they sure as hell will repeat it everywhere.

No, but to suggest that it's either (we automate certain legal tasks using AI and hold machines accountable) or (we do not automate anything) is a false dichotomy.

The point is that you expend a lot of effort into the engineering problem that is ensuring, to the absolute best of your ability, that what the AI gives you back is correct. Then the humans still verify it. One could then ask whether that doesn't just make the whole automation process redundant, but I don't think so. There are ways to make the verification process much easier. For example, direct links to and quotes from every cited thing, and so on.

> it's very difficult to disagree with anyone of the caliber of this man

Did you seriously write this with a straight face?

A family member works as a paralegal, and they have way more work than they can deal with. Their estate people have 70 cases per person that are mostly waiting on people to have time to work on them. Speeding this up can mean more billable hours quicker, depending on how the speedup works, and then they can just take on more cases.

It's always been a silly argument that's also predicated on a massive fallacy which everybody is aware of but seem to conveniently ignore during these arguments: that humans never make mistakes.

On top of that, dealing with text is literally what LLMs are all about.

The problem with accuracy, hallucinations and just generally ensuring responses are grounded in factual stuff is in large part and engineering problem.

Am I the only one who reads "vibecoded" as a negative word?

As far as I'm concerned, that's a term for shit software built by people using AI with minimal oversigt and quality control and often no idea what they're doing.

Using AI as a tool, carefully, would then be "agentic engineering".