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

Agent Client Protocol (ACP)

agentclientprotocol.com

Post reply on HN
Print view View original

71–80 of 104 posts

Re: Agent Client Protocol (ACP)

#71

Post by verdverm »

Disposal8433 wrote: post #13
mg wrote: post #10

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…

> 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.

Writing prompts makes these issues way less significant and makes the agents way more capable.

Prompt / context engineering is still an underrated and underutilized activity (imo)

Re: Agent Client Protocol (ACP)

#72

Post by verdverm »

Disposal8433 wrote: post #25
salomonk_mur wrote: post #18

Earlier quoted context omitted.

Hard disagree. LLMs are now incredibly good for any coding task (with popular languages).

You can't disagree with facts. Every time I try to give a chance to all those LLMs, they always use old APIs, APIs that don't exist, or mix things up. I'll still try that once a month to see how it evolves, but I have never been amazed by the capabilities of those things. > with popular languages Don't know, don't care. I write C++ code and that's all I need. JS and React can die a painful death for all I care as the…

> You can't disagree with facts. Every time I...

Anecdotes are not facts, they are personal experiences, which we know are not equal and often come with biases

Re: Agent Client Protocol (ACP)

#73

Post by Aeolun »

iamkd wrote: post #63
giancarlostoro wrote: post #8

Earlier quoted context omitted.

I'm basically sold on Zed, it has everything I have wanted from an editor for years, and that's without the amazing other things that they added that I wasn't even envisioning. For years I've prototyped a few different editors because of frustration with the status quo. There's a lot of work that goes into a good editor, and Zed has definitely done the legwork. I welcome them openly collaborating.

Zed is awesome, but the absence of side-by-side diffs just drives me crazy, so I'm back to Cursor / VSCode. Turns out I can't work without it. This is the top rated discussion on Github though: https://github.com/zed-industries/zed/discussions/26770

I’m sure anyone invested enough could contribute that xD

Like, I agree that that’s the thing I want most out of Zed right now, but not enough to do it myself.

Re: Agent Client Protocol (ACP)

#74

Post by verdverm »

th0ma5 wrote: post #68
dingnuts wrote: post #52

Earlier quoted context omitted.

If you want them to not make shit up, you have to load up the context with exactly the docs and code references that the request needs. This is not a trivial process and ime it can take just as long as doing stuff manually a lot of the time, but tools are improving to aid this process and if the immediate context contains everything the model needs it won't hallucinate any worse than I do when I manually enter code (…

So, I've done this, I've pasted in the headers and pleaded with it to not imagine ABIs that don't exist, and multiple models just want to make it work however they can. People shouldn't be so quick to reply like this, many people have tried all this advice... It also doesn't help that there is no independent test that can describe these issues, so all there is anecdote to use a different vendor or that the person mus…

There is a significant gap between agents and models.

Agents use multiple models, can interact with the environment, and take many steps. You can get them to reflect on what they have done and what they need to do to continue, without intervention. One of the more important things they can do is understand their environment, the libraries and versions in use, fetch or read the docs, and then base their edits on those. Much of the hallucinating SDKs can be removed with this, and with running compile to validate, they get even better.

Models typically operate in a turn-by-turn basis with only the context and messages the user provides.

Re: Agent Client Protocol (ACP)

#75

Post by Aeolun »

lvl155 wrote: post #30

Why don’t they focus on IDE first? I still can’t use their IDE as my daily. They also need to hire someone for UI. It took me 10 minutes to figure out how to bring up their AI chat window.

If it took you 10 minutes to bring that up I can’t understand why. Presumably you’ve switched to any of the other panels in Zed before?

Re: Agent Client Protocol (ACP)

#76

Post by 80hd »

quotemstr wrote: post #32
salomonk_mur wrote: post #18

Earlier quoted context omitted.

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?

Not OP but my two cents - probably laziness and propensity towards daydreaming.

I have extreme intolerance to boredom. I can't do the same job twice. Some people don't care.

This pain has caused me to become incredibly effective with LLMs because I'm always looking for an easier way to do anything.

If you keep hammering away at a problem - i.e. how to code with LLMs - you tend to become dramatically better at other people who don't do that.

Re: Agent Client Protocol (ACP)

#77

Post by Eisenstein »

quotemstr wrote: post #65
Eisenstein wrote: post #64

Earlier quoted context omitted.

Thought experiment: you can ride a bike. You can see other people ride bikes. Some portion of people get on a bike and fall off, then claim that bikes are not useful for transportation. Specify what skill they are lacking without saying 'ability to ride a bike'.

For a bike? Balance, fine motor control, proprioception, or even motivation. You can always break it down.

Knowing those things won't help them acquire the skill. What will help them be able to ride a bike is practicing trying to riding a bike until they can do it.

Re: Agent Client Protocol (ACP)

#79

Post by csomar »

I feel these solutions are approaching the problem backward. What I want is not a Claude Code in my Neovim but a Neovim in my Claude Code. That is, when the agent fails, I am able to hop in momentarily with all the perks of an IDE (ie: type-setter, LSP, etc.) and do some editing and then give control back to the agent.

Re: Agent Client Protocol (ACP)

#80

Post by 9dev »

giancarlostoro wrote: post #8
cube2222 wrote: post #4

Fingers crossed for this - it seems like Zed is kinda “going back to the roots” (of working on collaboration) and leaving this in place to disrupt the agentic IDE category (and make themselves not have to spend time on competing in it). Curious to see how adoption among cli agents will go (it’s nice to see Gemini cli already in). The level of competition in the LLM and coding assistant market is always nice to see, a…

I'm basically sold on Zed, it has everything I have wanted from an editor for years, and that's without the amazing other things that they added that I wasn't even envisioning. For years I've prototyped a few different editors because of frustration with the status quo. There's a lot of work that goes into a good editor, and Zed has definitely done the legwork. I welcome them openly collaborating.

You can take my IntelliJ IDE out of my cold, dead hands. I don’t understand why anyone would want to miss out on all the automatic inference and interlinked code base, the integrated tooling… Every time I try something like Zed or VS Code, I end up disappointed or install a no longer supported plugin only to learn it falls way short.

Yes, Zed's startup time is way better, and it definitely feels snappier. But when I work on code, I need to jump around the code. I want the debugger to show me the current line in the file, annotating the value of every variable right in the source. I want to jump to property usages. I want to automatically rename a function everywhere intelligently, not using search-replace. I want to get completion for my database tables, and browse them from the IDE. And lots more.

Post reply on HN