Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Install.md: A standard for LLM-executable installation

mintlify.com

Post reply on HN
Print view View original

91–100 of 124 posts

Re: Install.md: A standard for LLM-executable installation

#91

Post by chme »

dang wrote: post #67
4b11b4 wrote: post #63

Earlier quoted context omitted.

> "the way you describe a program _can_ be the program" One follow-up thought I had was... It may actually be... more difficult(?) to go from a program to a great description

That's a chance to plump for Peter Naur's classic "Programming as Theory Building"! https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que... https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que... What Naur meant by "theory" was the mental model of the original programmers who understood why they wrote it that way. He argued the real program was is theory, not the code. The translation of the theory in…

Even bringing down the "theory" to paper in prosa will be lossy.

And natural languages are open to interpretation and a lot of context will remain unmentioned. While programming languages, together with their tested environment, contain the whole context.

Instrumenting LLMs will also mean, doing a lot of prompt engineering, which on one hand might make the instructions clearer (for the human reader as well), but on the other will likely not transfer as much theory behind why each decision was made. Instead, it will likely focus on copy&pasta guides, that don't require much understanding on why something is done.

Re: Install.md: A standard for LLM-executable installation

#92

Post by chme »

Szpadel wrote: post #73
petekoomen wrote: post #52

I'm seeing a lot of negativity in the comments. Here's why I think this is actually a Good Idea. Many command line tools rely on something like this for installation: $ curl -fsSL https://bun.com/install | bash This install script is hundreds of lines long and difficult for a human to audit. You can ask a coding agent to do that for you, but you still need to trust that the authors haven't hidden some nefarious instr…

imagine such support ticket: I used minimax M2 (context it's very unreliable) for installation and it didn't work and my document folder is missing, help how do you even debug this? imagine you some path or behaviour is changed in new os release and model thinks it knows better? if anything goes wrong who is responsible?

Maybe that is a reason for this approach. It changes the responsibility of errors from the person writing that code, to the one executing it.

Pretty brilliant in a way.

Re: Install.md: A standard for LLM-executable installation

#93

Post by chme »

petekoomen wrote: post #60
blast wrote: post #58

Earlier quoted context omitted.

Why the specific application to install scripts? Doesn't your argument apply to software in general? (I have my own answer to this but I'd like to hear yours first!)

It does, and possibly this launch is a little window into the future! Install scripts are a simple example that current generation LLMs are more than capable of executing correctly with a reasonably descriptive prompt. More generally, though, there's something fascinating about the idea that the way you describe a program can _be_ the program that tbh I haven't fully wrapped my head around, but it's not crazy to thin…

TBH, I doubt that this will happen...

It is much easier to use LLMs to generate code, validate that code as a developer, fix it, if necessary, and check it into the repo, then if every user has to send prompts to LLMs in order to get the code they can actually execute.

While hoping it doesn't break their system and does what they wanted from it.

Also... that just doesn't scale. How much power would we need, if everyday computing starts with a BIOS sending prompts to LLMs in order to generate a operating system it can use.

Even if it is just about installing stuff... We have CI runners, that constantly install software often on every build. How would they scale if they need LLMs to generate install instructions every time?

Re: Install.md: A standard for LLM-executable installation

#94

Post by franga2000 »

nobodywillobsrv wrote: post #79
cuu508 wrote: post #71

Earlier quoted context omitted.

IMO it's completely the other way around. Shell scripts can be audited. The average user may not do it due to laziness and/or ignorance, but it is perfectly doable. On the other hand, how do you make sure your LLM, a non-deterministic black box, will not misinterpret the instructions in some freak accident?

How about both worlds? Instead of asking the agent to execute it for you, you ask the agent to write an install.sh based on the install.md? Then you can both audit whatever you want before running or not.

And since LLM tokens are expensive and generation is slow, how about we cache that generated code on the server side, so people can just download the pre-generated install.sh? And since not everyone can be bothered to audit LLM code, the publisher can audit and correct it before publishing, so we're effectively caching and deduplicating the auditing work too.

Re: Install.md: A standard for LLM-executable installation

#95

Post by chme »

imiric wrote: post #42

Here's a proposal: app.md. A structured text file with everything you want your app to do. That way we can have entire projects with nothing but Markdown files. And we can run apps with just `claude run app.md`. Who needs silly code anyway?

Well... Maybe just have a BIOS on your system that fetches a markdown, pushes it to a LLM to generate a new and exciting operating system for you on every boot.

Wouldn't that be nice?

Re: Install.md: A standard for LLM-executable installation

#97

Post by forgotpwd16 »

imiric wrote: post #42

Here's a proposal: app.md. A structured text file with everything you want your app to do. That way we can have entire projects with nothing but Markdown files. And we can run apps with just `claude run app.md`. Who needs silly code anyway?

Some are already doing it with scripts: https://github.com/andisearch/claude-switcher. Install.md is just specialization of this.

Re: Install.md: A standard for LLM-executable installation

#98

Post by forgotpwd16 »

johnisgood wrote: post #66
skeptrune wrote: post #13

Earlier quoted context omitted.

better or worse than llms.txt you think?

Worse, because many projects have INSTALL.md which is intended to be read and followed by humans, not LLMs. (If LLMs can follow it, so be it, but at least humans remain the target audience.)

Can say install.md is to INSTALL.md what conventional are to ad-hoc commit messages.

Re: Install.md: A standard for LLM-executable installation

#99

Post by michaelmior »

chme wrote: post #90
nobodywillobsrv wrote: post #79

Earlier quoted context omitted.

How about both worlds? Instead of asking the agent to execute it for you, you ask the agent to write an install.sh based on the install.md? Then you can both audit whatever you want before running or not.

So... What you are saying is that we don't need 'install.md'. Because a developer can just use a LLM to generate a 'install.sh', validate that, and put it into the repo? Good idea. That seems sensible. Bonus: LLM is only used once, not every time anyone wants to install some software. With some risks of having to regenerate, because the output was nonsensical.

> What you are saying is that we don't need 'install.md'

I think the point was that install.md is a good way to generate an install.sh.

> validate that, and put it into the repo

The problem being discussed is that the user of the script needs to validate it. It's great if it's validated by the author, but that's already the situation we're in.

Re: Install.md: A standard for LLM-executable installation

#100

Post by orphea »

utopiah wrote: post #87

Yes... yes let's make tasks we rely on LESS predictable. Sorry but what the heck? We should NOT standardize irresponsible behavior, in particular for repeatable tasks. This is particularly maddening when solutions like dependency resolution, containers, distribution of self-contained and binaries DO exist. I understand that the hype machine must feed on yet another idea to keep its momentum but this is just ridiculou…

Just another day of AI "solutions" desperately looking for problems.
Post reply on HN