Another discussion on the same topic from 3 days ago:
Agent Client Protocol (ACP)
31–40 of 104 posts
Re: Agent Client Protocol (ACP)
#32Earlier quoted context omitted.
> 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.
Hard disagree. LLMs are now incredibly good for any coding task (with popular languages).
What's your explanation for why others report difficulty getting coding agents to produce their desired results?
And don't respond with a childish "skill issue lol" like it's Twitter. What specific skill do you think people are lacking?
Re: Agent Client Protocol (ACP)
#33Earlier quoted context omitted.
In languages with strong compile-time checks (like say rust) the obvious problems can mostly be solved by having the agent try to compile the program as a last step, and most agents now do that on their own. In cases where that doesn't work (more permissive languages like python, or http APIs) you can have the AI write tests and execute them. Or ask the AI to prototype and test features separately before adding them…
> the obvious problems can mostly be solved by having the agent try to compile the program The famous "It compiles on my machine." Is that where engineering is going? Spending $billions to get the same result as the laziest developer ever?
If it compiles on my machine then the library and all called methods exist and are not hallucinated. If it runs on my machine then the called external APIs exist and are not hallucinated
That obviously does not mean that it's good software. That's why the rest of my comment exists. But "AI is hallucinating libraries/APIs" is something that can be trivially solved with good software practices from the 00s, and that the AI can resolve by itself using those techniques. It's annoying for autocomplete AI, but for agents it's a non-issue
Re: Agent Client Protocol (ACP)
#34I would love it, but please don't add JSON-RPC to the world... It's too heavy for editor.
Is there a better option?
Re: Agent Client Protocol (ACP)
#35I really wish Anthropic will adopt this for Claude Code, and I hope it provides at least the kind of integration they have with VS Code. Would be nice if it had access to at least diagnostics from the editor.
Re: Agent Client Protocol (ACP)
#36I would love it, but please don't add JSON-RPC to the world... It's too heavy for editor.
Anyone else noticing an uptick in confidently stated nonsense on HN? To write that JSON-RPC is "too heavy for editor", you have to not only misunderstand the cost of JSON encoding (trivial) but also the frequency of editor-tool interaction (seldom) and volume of data transferred (negligible). In addition, you have to look at LSP, MCP, and other JSON-y protocols and say "yep. There's where the UI latency is. Got it.". (Nope)
Are people who assert that JSON-RPC is "heavy" writing code we all rely on?
Re: Agent Client Protocol (ACP)
#37Claude, come up with a protocol for communicating between AI agents and IDEs/editors. Create node, python and rust libraries. Create a website with a landing page
lol. So hedonistic.
Re: Agent Client Protocol (ACP)
#38I'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…
I don't let it commit. I almost always need to modify its work in one way or another.
Most of the time I don't bother reprompting it either. If it doesn't understand the first time then I'm better off making the change myself, rather than sink time into a cycle of reprompting and rejection.
On the other hand, if it understands what I want the first time I have more confidence that it's on the same wavelength as me.
Re: Agent Client Protocol (ACP)
#39With already https://agentcommunicationprotocol.dev (ACP) same name seems confusing now. even though differences are there in both.
IBM announced in March 2025 its Agent Communication Protocol (ACP) but is now abandoning the ACP name and merging ACP efforts with Google’s Agent2Agent (A2A) protocol at the Linux Foundation. The ACP team is winding down as the industry backs A2A for open, community-driven AI agent interoperability under Linux Foundation governance. This move aims to unify protocols and avoid fragmentation in AI agent standards.
https://lfaidata.foundation/communityblog/2025/08/29/acp-joi...
Re: Agent Client Protocol (ACP)
#40The protocol for interacting with code is files and text. You need to define an interface for Ai to click buttons? Or to create keyboard macros that simulate clicking buttons? We are all doomed!
There's a long history of REPL interaction protocols decoupling development environments from tools and making things nicer overall. This thing is an empty in the same tradition. (That said, I'm not convinced its author knew the tradition existed.)
It's like the Jupyter protocol, from which people do derive utility.