Live data from Hacker News

Show HN: Axe – A 12MB binary that replaces your AI framework

github.com

121–130 of 145 posts

Re: Show HN: Axe – A 12MB binary that replaces your AI framework

#121

I've had good success with something along these lines but perhaps a bit more raw: - claude takes a -p option - i have a bunch of tiny scripts, each script is an agent but it only does one tiny task - scripts can be composed in a unix pipeline For example: $ git diff --staged | ai-commit-msg | git commit -F - Where ai-commit-msg is a tiny agent: #!/usr/bin/env bash # ai-commit-msg: stdin=git diff, stdout=conventional…

I was looking at something similar. What does your agent-lib.sh look like?

Something like this: https://github.com/craigjperry2/tiny-agents/blob/main/lib/ag...

Re: Show HN: Axe – A 12MB binary that replaces your AI framework

#122

I've had good success with something along these lines but perhaps a bit more raw: - claude takes a -p option - i have a bunch of tiny scripts, each script is an agent but it only does one tiny task - scripts can be composed in a unix pipeline For example: $ git diff --staged | ai-commit-msg | git commit -F - Where ai-commit-msg is a tiny agent: #!/usr/bin/env bash # ai-commit-msg: stdin=git diff, stdout=conventional…

Do you have examples of these commit messages? I have yet to see an AI write a good commit message. At least when compared to good commit messages -- if it just does better than "wip" or "fix stuff" that's not a high bar.

My skills/domain/git.md looks like this:

    Context: You are working with Git repositories.
    - Commit messages follow Conventional Commits: type(scope): description
    - Types: feat, fix, docs, refactor, test, chore, ci, perf
    - Subject line max 72 chars, imperative mood, no trailing period
    - Reference issue numbers when relevant
So it produces messages like:

    $ git diff HEAD~1 | bin/ai-commit-msg
    fix(guards): pass input to claude and tighten verdict handling

Re: Show HN: Axe – A 12MB binary that replaces your AI framework

#123
Interesting approach to slimming down the framework layer. One thing I've been thinking about as agents get lighter and faster the attack surface for prompt injection and behavioral drift grows. Are you thinking about any security primitives at this layer?

Re: Show HN: Axe – A 12MB binary that replaces your AI framework

#124

Earlier quoted context omitted.

Do you have examples of these commit messages? I have yet to see an AI write a good commit message. At least when compared to good commit messages -- if it just does better than "wip" or "fix stuff" that's not a high bar.

My skills/domain/git.md looks like this: Context: You are working with Git repositories. - Commit messages follow Conventional Commits: type(scope): description - Types: feat, fix, docs, refactor, test, chore, ci, perf - Subject line max 72 chars, imperative mood, no trailing period - Reference issue numbers when relevant So it produces messages like: $ git diff HEAD~1 | bin/ai-commit-msg fix(guards): pass input to c…

My issue with this kind of message is that it doesn't convey intent well enough. This kind of commit message will always be like "remove check from handleUser" instead of "fix authorization in xyz case". But I assume these are different schools of commits -- I prefer commits which convey WHY, not WHAT, much like source code comments.

Re: Show HN: Axe – A 12MB binary that replaces your AI framework

#125

Earlier quoted context omitted.

Clankers are not humans.

This is the second time I've seen somebody use the word "clankers" in the last couple days to refer to AI. Is that a thing now? Where'd that come from? Gonna be honest, it has taken away from the message both times I've seen it. It feels a bit like you're LARPing your favorite humans vs robots tv show.

It mostly sounds like people who are desperate to use racist slurs and have finally found a(nother) public outlet for it.

Re: Show HN: Axe – A 12MB binary that replaces your AI framework

#128

Earlier quoted context omitted.

Clankers are not humans.

This is the second time I've seen somebody use the word "clankers" in the last couple days to refer to AI. Is that a thing now? Where'd that come from? Gonna be honest, it has taken away from the message both times I've seen it. It feels a bit like you're LARPing your favorite humans vs robots tv show.

"Clanker" is a sign that we're dealing with a Blade Runner, and better be careful
Post reply on HN