←back to thread

Agent Client Protocol (ACP)

(agentclientprotocol.com)
270 points vinhnx | 2 comments | 30 Aug 25 12:42 UTC | HN request time: 0s | source
Show context
mg ◴[30 Aug 25 14:02 UTC] No.45074786[source]▶
I'm fine with treating AI like a human developer:

I ask AI to write a feature (or fix a bug, or do a refactoring) and then I read the commit. If the commit is not to my liking, I "git reset --hard", improve my prompt and ask the AI to do the task again.

I call this "prompt coding":

https://www.gibney.org/prompt_coding

This way, there is no interaction between my coding environment and the AI at all. Just like working with a human developer does not involve them doing anything in my editor.

replies(2): >>45074878 #>>45076374 #
Disposal8433 ◴[30 Aug 25 14:16 UTC] No.45074878[source]▶
> Nowadays, it is better to write prompts

Very big doubt. AI can help for a few very specific tasks, but the hallucinations still happen, and making things up (especially APIs) is unacceptable.

replies(6): >>45074958 #>>45074999 #>>45075081 #>>45075111 #>>45079473 #>>45081297 #
1. mg ◴[30 Aug 25 14:48 UTC] No.45075111[source]▶
Do others here encounter that problem? I never do. I can't remember the last time I saw a hallucination in a commit.

Maybe it's because the libraries I use are made from small files which easily fit into the context window.

replies(1): >>45077019 #
2. brulard ◴[30 Aug 25 18:45 UTC] No.45077019[source]▶
Same here, very low hallucination rate and it can pretty quickly correct itself (Claude Code). To force it to use recent versions of libraries instead of old ones, it's good to have it specifically required in CLAUDE.md and also having docs MCP (like context7) can help.