←back to thread

Claude Code now supports hooks

(docs.anthropic.com)
381 points ramoz | 8 comments | | HN request time: 2.03s | source | bottom
1. artursapek ◴[] No.44429368[source]
adding a hook to have it push to prod every time baby
replies(3): >>44429542 #>>44429613 #>>44430104 #
2. apwell23 ◴[] No.44429542[source]
you can just tell it do that or in your claude.md. don't need hooks
replies(1): >>44429577 #
3. thelittleone ◴[] No.44429577[source]
In some cases cc misses rules in CLAUDE.md.
replies(1): >>44429734 #
4. thelittleone ◴[] No.44429613[source]
This also:

1) Assign coding task via prompt 2) Hook: Write test for prompt proves 3) Write code 4) Hook: Test code 5) Code passes -> Commit 6) Else go to 3.

5. ramoz ◴[] No.44429734{3}[source]
In many cases.
replies(1): >>44429775 #
6. apwell23 ◴[] No.44429775{4}[source]
so its back to hand coding stuff again.

They are going to slowly add "features" that brings handcoding back till its like 100% handcoding again.

replies(1): >>44430201 #
7. bgwalter ◴[] No.44430104[source]
We have to do this, otherwise China wins the "AI" race!
8. ramoz ◴[] No.44430201{5}[source]
This doesn’t come without consideration. You can see I mention this in the original feature request.

Yes - it’s fine to think of it as handholding (or handcoding). These model providers cannot be responsible for ultimate alignment with their users. Today, they can at best enable integration so a user, or business, can express and ensure their own alignment at runtime.

The nature of these systems already requires human symbiosis. This is nothing more than a new integration point. Will empower agents beyond today’s capabilities, increase adoption.