Sure, here's a summary of the themes from the Hacker News discussion:
editor preferences and loyalty
The discussion highlights a strong divide among users regarding their preferred code editors, with many expressing fierce loyalty to established IDEs like IntelliJ and PyCharm, while others are drawn to newer, more experimental editors like Zed, or are happy with VS Code due to convenience and ecosystem support.
"You can take my IntelliJ IDE out of my cold, dead hands. I donāt understand why anyone would want to miss out on all the automatic inference and interlinked code base, the integrated toolingā¦ 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." - 9dev
"Iām 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." - giancarlostoro
"I would riot if i couldn't use Pycharm anymore, for big python projects just nothing beats it right now." - mvATM99
"I was an avid JetBrains user until I needed to work with Elixir. You simply canāt do Elixir in their IDEs. So I switched to VS Code. After more than a year of using VS Code, you develop muscle memory for it. At this point, I donāt really care about the differences anymore and Iām happy with VS Code." - k9294
"I still canāt 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." - lvl155
"VSCode. ... Feels like a lot of mindshare has shifted towards VSCode, so that's where the tooling investment goes. I don't want to be forced off of subl because new tools stop supporting it - it's a great editor, and it's not sponsored by a massive company." - bsimpson
The desire for Editor-Agent Standardization and Interoperability
A central theme is the need for standardized protocols for communication between AI coding agents and editors. This aims to avoid a fragmented ecosystem where each agent needs custom integration with every editor, and vice-versa. The proposed Agent Communication Protocol (ACP) is seen as a potential solution.
"This is the equivalent of LSP but for coding agents. So any editor does not have to rebuild an interface to support each and every new one." - baggiponte
"The question is whyā¦ The purpose of an ide is to pull together the tools a developer needs to develop softwareā¦ But coding agents seem to already be able to use the command line and mcp quite well to do this. So why mediate using these tools through an IDE (over a new protocol) rather than just using the tools directly through the command line or mcp? Itās two extra levels of indirection, so there needs to be a really good reason to do it." - jmull
"The IDE is in-between because it asks the user for confirmation before doing anything, if that's what you are asking. It's not adding any indirection or something, this is just how coding agents talk to the IDE already, all this does is standardize the language they speak which would be a win for everybody." - lyu07282
"I donāt see why we need so many protocols. In such a greenfield tech, many are eager to define rules. Thereās already a protocol called AG-UI that does the similar thing, but even its purpose isnāt entirely clear to me. Rather than rushing to create standards, I think the focus should be on building practical implementations, AI-centric UI components that actually help developers design more AI-friendly interfaces. Once the space matures and stabilizes, thatās when standardization will make more sense. Right now, it feels too early." - hari-trata
"One great reason is to avoid MN problem: https://matklad.github.io/2022/04/25/why-lsp.html" - ivanjermakov*
"I hope it gains traction. One thing that is not clear to me is file search vs unsaved files. It's common for agents to use, e.g., ripgrep to search the file system. But if the communication protocol includes read/write access to unsaved files, there is a desync in terms of accuracy.. rg can't search unsaved files." - vlaaad
"Iāve been writing a tool to enable Claude Code to use ACP (because I use CC and Zed a lot) and so far Iāve been pretty successful (using the Claude Code SDK and the ACP Client library) although there are some rough edges. I will polish it a little bit and publish it tomorrow I guess." - rmonvfer
"I hope it changes that." (referring to ACP standardizing protocols for AI features in editors like Helix) - akattelu
"There should be a protocol for communicating between AI agents and IDEs/editors. Create node, python and rust libraries. Create a website with a landing page." - awestroke
"IBM announced in March 2025 its Agent Communication Protocol (ACP) but is now abandoning the ACP name and merging ACP efforts with Googleās 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." - schwentkerr (citing a blog post)
Debate on AI's current coding capabilities and limitations
A significant portion of the discussion revolves around the effectiveness of current LLMs and AI agents for coding tasks. Skepticism exists regarding their ability to avoid "hallucinations" and accurately use APIs, especially in larger or more complex codebases.
"but the hallucinations still happen, and making things up (especially APIs) is unacceptable." - Disposal8433
"The new models are much better at reading the codebase first, and sticking to "use the APIs / libraries already included". Also, for new libraries there's context7 that brings in up-to-date docs. Again, newer models know how to use it (even gpt5-mini works fine with it)." - NitpickLawyer
"What size of codebases are we talking here? I've had a lot of issues trying to do pretty much anything across a 1.7 million LOC codebase and generally found it faster to use traditional IDE functionalities." - sigseg1v
"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?" - Disposal8433
"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." - Disposal8433
"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 (but when I do it, I call it a typo)" - dingnuts
"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..." - th0ma5
"Anecdotes are not facts, they are personal experiences, which we know are not equal and often come with biases" - verdverm (responding to critiques of AI performance)
"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?" - quotemstr
"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." - 80hd (discussing skill development with LLMs)
"Maybe it's because the libraries I use are made from small files which easily fit into the context window." - mg (suggesting context window size as a factor in AI performance)
"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." - zarzavat
"It's surprising fine, as long as you allow the AI to iterate on its work. It will discover that it doesn't compile, and then maybe lookup the API and then it will most often fix it and move on. AI is no more capable of reliably one shotting solutions that you are." - tomjen3
Discussion on Protocol Design and Implementation Details
Users also engaged in discussions about the technical specifics of protocols like ACP, including naming conventions, underlying technologies (like JSON-RPC), and the best approach to standardization.
"Whatās your explanation for why others report difficulty getting coding agents to produce their desired results? And donāt respond with a childish "skill issue lol" like itās Twitter. What specific skill do you think people are lacking?" - quotemstr
"For a bike? Balance, fine motor control, proprioception, or even motivation. You can always break it down." - Eisenstein (responding to quotemstr's question about missing skills)
"I see they've also caught the RFC2119 bug. This "MUST", "SHALL", "MAY" thing is a linguistic blight on our standards landscape and should be eradicated. HTML5 is written without this unnecessary level of linguistic pretense and works fine. If your proposed spec is full of "SHALL", "MUST", and "MAY", I'm going to dock you ten points of credibility from the outset. It's a signal you've set out to imitate the vibes of seminal RFC specs without independently considering the substance." - quotemstr
"I don't know if your complaint is specifically about the capitalization, but I find these clear rules useful when interpreting specifications." - PhilipRoman
"But coding agents seem to already be able to use the command line and mcp quite well to do this. So why mediate using these tools through an IDE (over a new protocol) rather than just using the tools directly through the command line or mcp? Itās two extra levels of indirection, so there needs to be a really good reason to do it." - jmull
"The big question is why it can't be just a LSP server or extension to the LSP protocol to provide all that might be needed by the LLM." - greatgib
"I would love it, but please don't add JSON-RPC to the world... It's too heavy for editor." - acomagu
"Harsh. But fair. JSON-RPC is one of the leanest protocols out there." - willm (disagreeing with acomagu)
"Why donāt they focus on IDE first? I still canāt 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." - lvl155
"Naming things isn't that hard. at least put something with AI/LLM and code/IDE in the name." - Eduard
"How's this better than MCP?" - cranberryturkey
"Does anyone else find it funny that LLMs need a protocol to execute tooling? Like, it understands language, right?" - gijoeyguerra
Zed's direction and feature development
There's a discussion about Zed's strategic direction, with some interpreting its efforts with ACP as a way to focus on core editor features while letting agents handle AI integration, and others lamenting the lack of certain fundamental features within Zed itself.
"Fingers crossed for this - it seems like Zed is kinda āgoing back to the rootsā (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)." - cube2222
"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." - iamkd
"Aeolun: Iām sure anyone invested enough could contribute that xD Like, I agree that thatās the thing I want most out of Zed right now, but not enough to do it myself." - Aeolun (referencing iamkd's point about diffs)
"Really hope for this to get traction so Iām not bound to the usual IDE" - baggiponte
"Why donāt they focus on the IDE first? I still canāt 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." - lvl155
"If it took you 10 minutes to bring that up I canāt understand why. Presumably youāve switched to any of the other panels in Zed before?" - Aeolun (responding to lvl155)
"Zed should start improving the diff view. It's one of the worst. It does not even have word level diff highlight or split diff view" - xmorse
"Only reason I use VSCode these days is Git Merge Editor" - nicce