[rvz]

This has to be a joke right?

> Installing software is a task which should be left to AI.

Absolutely I don't think so. This is a very bad idea.

$ curl | bash was bad enough. But $ curl -fsSL | claude looks even worse.

What could possibly go wrong?

[andai]

I gave Claude root to my $3 VPS and I'm delighted to have a server that "configures itself."

I wouldn't use it for anything serious, but that being said, I think it's in better shape than when I was running it.

[skeptrune]

fascinating. i personally (biased bc i work at Mintlify) think a markdown file makes more sense than a bash script because at least Claude kind of has your best interests at heart.

[constantcrying]

>i personally (biased bc i work at Mintlify) think a markdown file makes more sense than a bash script because at least Claude kind of has your best interests at heart.

Most of the largest trends in "how to deploy software" revolve around making things predictable and consistent. The idea of abandoning this in favor of making a LLM do the work seems absurd. At least the bash script can be replicated exactly across machines and will do the same thing in the same situation.

[skeptrune]

Yeah, I'm going to add that as one of the downsides to the docs. The stochastic nature of the markdown vs. a script is for sure a reason to not adopt this.

[vimda]

Tell that to the weekly thread where Claude nukes your home directory or similar

[heliumtera]

>Claude kind of has your best interests at heart.

That is such a wild thing to say. Unless this whole thing is satire...

[skeptrune]

Wait, but being serious. You can prompt the ai when you feed it this file to ask "do you see anything nefarious" or "follow these instructions, but make sure you ask me every time you install something because i want to check the safety" in a way that you can't when you pipe a script into bash.

Does that make any sense or am I just off my rocker?

[themikesanto]

You can do the same thing with any install script you might come across today.

[skeptrune]

True, that's a fair point. Do you think there's any merit to the idea that the UX of asking about a markdown file is more natural than a bash script?

[inlined]

No. Absolutely not. The opposite in fact. Your bash script is deterministic. You can send it to 20 AIs or have someone fluent read it. Then you can be confident it’s safe.

An LLM will run the probabilistically likely command each time. This is like using Excel’s ridiculous feature to have a cell be populated by copilot rather than having the AI generate a deterministic formula.

[imiric]

[flagged]

[nathan_compton]

I try to have my brain have my best interests at heart, personally.

[esalman]

> Claude kind of has your best interests at heart

How we've all been blue-pilled. Sigh..