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

Files are the interface humans and agents interact with

madalitso.me

Post reply on HN
Print view View original

101–110 of 144 posts

Re: Files are the interface humans and agents interact with

#101

Post by lozenge »

Gigachad wrote: post #85
staplung wrote: post #51

Not knocking the article in any way but from the headline I was expecting - perhaps hoping - this would be about some innovation in filesystems research like it was the 90's again. That's not what this is. It's about how filesystems as they are (and have been for decades) are proving to be powerful tools for LLMs/agents.

I feel like every article on HN now disguises itself as interesting but the content is just the same boring AI slop.

I don't think the contents is AI sklop at all. It just haooens to be abiut AI.

Re: Files are the interface humans and agents interact with

#102

Post by packetlost »

andai wrote: post #99
packetlost wrote: post #62

We once again discover that Plan9 and UNIX were right. The most powerful, lowest common denominator interface is text files exposed over a file system. Now to get back to making 9p2026. The article gets some fundamentals completely wrong though: file systems are full graphs, not strict trees and are definitely not acyclic

So what are Plan 9's killer features, and can they be bolted on with FUSE or is there a deeper magic at play?

Plan9 doesn't really have a single killer feature beyond 9P and the universal consistency and simplicity of its APIs. It has a very clean syscall interface and takes "everything is a file" to its logical conclusion and does it well (IMO). Pretty much everything is a file(system) and it's all accessed via the 9P protocol.

You could sorta bolt these features on with FUSE, but to see real benefits you'd want something closer to Inferno, which is like an OS/application runtime that runs on top of another OS host.

In my mind, the security model is the closest thing to a killer feature it has. Because everything is a file(system) and the fork/rfork and bind syscalls let you precisely control what resources/files/services/etc. a child process has access to via easily understandable shell commands (or using libc functions if you want), it means you don't need special APIs for namespacing (ie. containers) and access controls. It's very clean. When a parent process forks or spawns a child process, it can chose whether that process inherits the namespace or gets a clean slate that it can then bind filesystems onto, controlling precisely what it has access to.

Re: Files are the interface humans and agents interact with

#103

Post by tasuki »

> He pointed out that Claude Code works because it runs on your computer, with your environment, your data, your context.

Ah yes - I hate that. Yes it "works", but I don't want things to only work on my machine: I want them to work everywhere.

I was wondering why Google's Jules wasn't more popular, and I guess this is why. My preference for my code to work in different environments is unusual.

Re: Files are the interface humans and agents interact with

#104

Post by XorNot »

lozenge wrote: post #101
Gigachad wrote: post #85

Earlier quoted context omitted.

I feel like every article on HN now disguises itself as interesting but the content is just the same boring AI slop.

I don't think the contents is AI sklop at all. It just haooens to be abiut AI.

At this point those are about the same in terms of quality.

"I spent money writing "a prompt* and this is what I learned".

Re: Files are the interface humans and agents interact with

#105

Post by bsenftner »

visarga wrote: post #70
bsenftner wrote: post #23

I don't think this paradigm will last, or be what becomes the more common structure in the future. This will still suffers from conflicts of persona and objective, plus has the issue that individual apps will need protected file hierarchies to prevent malicious injections. I don't see this as a solution, just a deck chair shuffle. I've been researching and building with a different paradigm, an inversion of the tool…

Your project, while interesting as an approach, is orders of magnitude more complex than the proposition here - which is to rely on agents skills with file systems, bash, python, sed, grep and other cli tools to find and organize data, but also maintain their own skills and memories. LLMs have gained excellent capabilities with files and can generate code on the fly to process them. It's people realizing that you can…

It ends up being similar to how early PC software was written before people realized malicious software could be running. There used to be little to no memory safety between running programs, and this treatment of files as the contextual running memory is similar. It's a great idea until a security perspective is factored in. It will need to end up being very much like closed applications and their of writing proprietary files, which will need some security layer that is not there yet.

Re: Files are the interface humans and agents interact with

#107

Post by anthk »

andai wrote: post #99
packetlost wrote: post #62

We once again discover that Plan9 and UNIX were right. The most powerful, lowest common denominator interface is text files exposed over a file system. Now to get back to making 9p2026. The article gets some fundamentals completely wrong though: file systems are full graphs, not strict trees and are definitely not acyclic

So what are Plan 9's killer features, and can they be bolted on with FUSE or is there a deeper magic at play?

namespaces and no difference between local and remote devices. You just bind directories. FUSE it's a dog slow toy in comparison.

You don't even need root permissions to do tons of stuff in 9front with filesystems. You don't even need a root account.

Re: Files are the interface humans and agents interact with

#109

Post by therealdrag0 »

orsorna wrote: post #11
q3k wrote: post #9

Earlier quoted context omitted.

Everyone's trying to be the new thought leader enlightened technical essayist. So much fluff everywhere.

What's wild is that with a few minutes of manual editing it would give exponential return. For instance, a lead sentence in your section saying "here's why X" that was already described by your subheading is unnecessary and could have been wholly removed.

That’s pretty presumptive of how obviously the author could improve it. As someone who writes a lot of docs, I find feedback and preferences varies wildly. They may just have well made it “worse” to your preferences by hand editing it more.
Post reply on HN