alt Hacker NewsInstall.md: A standard for LLM-executable installation
Comments
All the insecurity of running a random bash script, with all the terrifying stochasticity of an LLM in one "makes you want to tear your eyes out" package!
Author should explore Ansible/Puppet/Chef.
I’m not sure this solution is needed with frontier models.
> "Installing software is a task which should be left to AI."
So, after teaching people to outsource their reasoning to an LLM, LLMs are now actively coaching folks to use LLMs for tasks for which it makes no sense at all.
What is the benefit of having this be a standard? Can't an agent follow a guide just as easily in document with similar content in a different structure?
I would think that the common bash scripts we already have would provide an agent better context for installation than a markdown file, and even better, they already work without an LLM.
This is a "solution" looking for a problem.
At some point in the future (if not already), claude will install malware less often on average. Just like waymos crash less frequently.
Once you accept that installation will be automated, standardized formats make a lot of sense. Big q is will this particular format, which seems solid, get adopted - probably mostly a timing question
I feel like I should create a project called 'Verify Node.js v20.17.0+' that is totally not malware.
I usually complain about proposed standards not being under the /.well-known namespace, but in this case, wow. I can't even comment.
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?
>Installing software is a task which should be left to AI
What?? How do I get off of this train? I used to come to hacker news for a reason...what the fuck am I reading
> Installing software is a task which should be left to AI.
Just like installing spice racks is a task which which should be left to military engineer corps.
>Installing software is a task which should be left to AI.
This is such an insane statement. Is this satire?
should've been posted on April 1st. would be better suited on that specific date! /s
Appropriately, I think this was probably drafted by AI too:
> How does install.md work with my existing CLI or scripts?
> install.md doesn't replace your existing tools—it works with them. Your install.md can instruct the LLM to run your CLI, execute your scripts, or follow your existing setup process. Think of it as a layer that guides the LLM to use whatever tools you've already built.
(It doesn't X — it Ys. Think of it as a Z that Ws. this is LLM speak! I don't know why they lean on these constructions to the exclusion of all else, but they demonstrably do. The repo README was also committed by Claude Code. As much as I like some of the code that Claude produces, its Readmes suck)