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

You need to rewrite your CLI for AI agents

justin.poehnelt.com

Post reply on HN
Print view View original

31–40 of 74 posts

Re: You need to rewrite your CLI for AI agents

#31

Post by utopiah »

lynx97 wrote: post #13

I love how AI gave the command-line and TUI interfaces a kind of Second Renaissance. It is not just AI that loves CLIs. It is especially blind people like me, who still use a lot of text-mode tools for their implicit accessibility. I gave codex a whirl recently, and hey! No accessibility problems at all. Just works. A few years back, that would have been released as a GUI-only program and would have locked me out com…

A second renaissance? The entire time internet had been running on CLI. All modern services relying om containers rely on images based on CLI. There is no renaissance needed because it never stopped.

Re: You need to rewrite your CLI for AI agents

#32

Post by bayindirh »

Haha, no.

I write my tools for humans, without help or use of AI. If the AI agent wants to use my tool so bad, they need to rise to that level. I'll not crouch on my knees to meet it.

If I ever write a tool for AI interaction, I'd give it a well-defined API, to make it even easier for the agent.

Re: You need to rewrite your CLI for AI agents

#34

Post by lynx97 »

utopiah wrote: post #31
lynx97 wrote: post #13

I love how AI gave the command-line and TUI interfaces a kind of Second Renaissance. It is not just AI that loves CLIs. It is especially blind people like me, who still use a lot of text-mode tools for their implicit accessibility. I gave codex a whirl recently, and hey! No accessibility problems at all. Just works. A few years back, that would have been released as a GUI-only program and would have locked me out com…

A second renaissance? The entire time internet had been running on CLI. All modern services relying om containers rely on images based on CLI. There is no renaissance needed because it never stopped.

Sure, server-side. What I am talking about is user-facing programs. That is why I mentioned codex as an example.

Re: You need to rewrite your CLI for AI agents

#35

Post by ZeroGravitas »

Some of this seems a bit overhyped.

I like CLI tools with json output that can be piped through jq. I've seen llms do that with existing tools.

The human needs and llm needs seem to overlap, especially if the human is using scripts and piping between tools.

The number of times it implies you didn't need to validate "human" input until llms arrived is scary too.

I'm also surprised to hear them say llms shouldn't Google, as that seems an area that Google themselves could optimize their search service for their llms and get an advantage.

Finally, I wonder if just using older, smaller llms is a valid fuzzing approach for clis (or anything else llms might be controlling). Or do you need a high powered llm trained to generate adversarial input?

Re: You need to rewrite your CLI for AI agents

#36

Post by justinwp »

sheept wrote: post #27
magospietato wrote: post #23

Earlier quoted context omitted.

Surely the skill for a cli tool is a couple of lines describing common usage, and a description of the help system?

Sure, but the post itself brags, > gws ships 100+ SKILL.md files Which must altogether be hundreds of lines of YAML frontmatter polluting your context.

You don't need to install all of them.

Re: You need to rewrite your CLI for AI agents

#40

Post by peddling-brink »

justinwp wrote: post #37
jeppeb wrote: post #9

The article states that agents work better with JSON than documented flags - that seems counterintuitive . How is this assumption validated?

Try building a CLI with a complex JSON as flags approach. :)

I just did the opposite and am seeing better results.

Claude was struggling to use the ‘gh’ command to reliably read and respond to code review line level comments because it had to use the api. I had it write a few simple command line tools and a skill for invoking it, instantly better results.

YMMV

Post reply on HN