I feel like I should create a project called 'Verify Node.js v20.17.0+' that is totally not malware.
Install.md: A standard for LLM-executable installation
31–40 of 124 posts
Re: Install.md: A standard for LLM-executable installation
#32[stub for offtopicness] Since the article has been changed to tone down its provocative opener, which clearly had a kicking-the-anthill effect, I'm moving those original reactions to this subthread.
Or just, I don’t know… package your software?
Intent here is that this would be adopted by more difficult to install devtools which are unpackaged to the extent that you need a dependency like a specific version of Node, Python, or a dev lib.
Re: Install.md: A standard for LLM-executable installation
#33Earlier quoted context omitted.
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.…
Yeah, removing that line right now. Went too fast and some this copy is definitely low quality :(. Incredibly ironic for me to say that AI needs more supervision while working at the company proposing this haha. Any other feedback you have about the general idea?
I think my preferred version of this would be a hybrid. Keep the regular installer, add a file filled with information that an LLM can use to assist a human if the install script fails for some reason.
If the installer was going to succeed in a particular environment anyway, you definitely want to use that instead of an LLM that might sporadically fail for no good reason in that same environment.
If the installer fails then you have a "knowledge base" to help debug it, usable by humans or LLMs, and if it fails, well, the regular installer failed too, so hopefully you're not worse off. If the user runs the helper LLM in yolo mode then the consequences are on them.
Re: Install.md: A standard for LLM-executable installation
#34Earlier quoted context omitted.
[flagged]
Fascinating. My thinking was that this is an upgrade over a bash script because you can prompt the AI to check it, clear installs with you, or otherwise investigate safety before installing in a way that isn't natural with *.sh. Does that make any amount of sense or am I just crazy?
Bash scripts give you visibility into what they are going to do by virtue of being machine instructions in a determimistic language. MD files you pipe to matrix multiplication has a much lower chance of being explainable.
Re: Install.md: A standard for LLM-executable installation
#35Earlier quoted context omitted.
Fascinating. My thinking was that this is an upgrade over a bash script because you can prompt the AI to check it, clear installs with you, or otherwise investigate safety before installing in a way that isn't natural with *.sh. Does that make any amount of sense or am I just crazy?
Time and time again, be it "hallucination", prompt injection, or just plain randomness, LLMs have proven themselves woefully insufficient at best when presented with and asked to work with untrusted documents. This simply changes the attack vector rather than solving a real problem
In a computing system, LLMs aren't substituting for code, they're substituting for humans. Treat them accordingly.
Re: Install.md: A standard for LLM-executable installation
#36Author should explore Ansible/Puppet/Chef.
I’m not sure this solution is needed with frontier models.
Re: Install.md: A standard for LLM-executable installation
#37Author should explore Ansible/Puppet/Chef. I’m not sure this solution is needed with frontier models.
Can you explain more? I see how those relate to a very limited extent, but I'm not getting your entire vision.
Re: Install.md: A standard for LLM-executable installation
#38[stub for offtopicness] Since the article has been changed to tone down its provocative opener, which clearly had a kicking-the-anthill effect, I'm moving those original reactions to this subthread.
I don’t understand how this made it to the front page
This is hacker news now. Nothing else here to see, only slop.
Everything here is: look what I prompted to take advantage of you
Re: Install.md: A standard for LLM-executable installation
#39Earlier quoted context omitted.
Yeah, removing that line right now. Went too fast and some this copy is definitely low quality :(. Incredibly ironic for me to say that AI needs more supervision while working at the company proposing this haha. Any other feedback you have about the general idea?
I think my preferred version of this would be a hybrid. Keep the regular installer, add a file filled with information that an LLM can use to assist a human if the install script fails for some reason. If the installer was going to succeed in a particular environment anyway, you definitely want to use that instead of an LLM that might sporadically fail for no good reason in that same environment. If the installer fai…
Acknowledged. The standard includes a link to the llms.txt for a site at the bottom which is intended to give it that "knowledge base" to query.
I think I agree with you on it needing to assist in event of failure instead of jumping straight to install though. Will think more about that.
Re: Install.md: A standard for LLM-executable installation
#40Earlier quoted context omitted.
You can do the same thing with any install script you might come across today.
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?
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.