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

Claude Code: Now in Beta in Zed

zed.dev

Post reply on HN
Print view View original

401–410 of 431 posts

Re: Claude Code: Now in Beta in Zed

#401

Post by kiney »

lemontheme wrote: post #364
dcre wrote: post #255

Glad to see this out so quickly. Like I said[0] on the Gemini announcement post, it feels like Zed is trying to get out of the business of iterating on agent logic and just let other people handle it. Any prompting secret sauce a) is trivial to copy, and b) gets eaten by the next model generation anyway. The capabilities of Claude Code, Codex, OpenCode, etc. seem to me to be converging. [0]: https://news.ycombinator.…

Plausible take. My first time using a coding agent was with Zed’s. As a sceptic, I was blown away. Two or weeks later Claude Code dropped and I haven’t used the Zed agent since. I canceled my subscription because 20 EUR/month for AI features I no longer use felt silly. And with the massive investment from Sequoia, and the real possibility of enshittification, I couldn’t mentally classify it as a monthly ‘donation’ to…

I use the zed agent regularly. What does claude code do better?

Re: Claude Code: Now in Beta in Zed

#402

Post by throwaway314234 »

jkkola wrote: post #128
mikeocool wrote: post #78

Earlier quoted context omitted.

Zed's main selling point over VSCode for me is the lack of a slight delay between when I press a key and when the character appears. VSCode has always felt ever so slightly sluggish to me, and I find it maddening as I type.

This is why I cannot switch to neovim despite my attempts. I love the workflow, but the delay is too noticeable for me, and nothing helps. It's not a long delay, but long enough for me to feel like I have to wait for hours compared to Zed.

May be Helix editor will be fast enough? In my opinion it feels considerably faster then vim with addons

Re: Claude Code: Now in Beta in Zed

#403

Post by conartist6 »

jryio wrote: post #149

What most of these comments are missing is the attempt at standardization and unification. There are a lot of comments that people need X feature in order to switch to Y editor. While that may be true and your particular workflow requires certain features, what is overlooked is the survival pressure for editors. It appears that our industry is moving towards adoption, sometimes mandatory, of AI coding agents. Regardl…

I'm sorry if this is blunt but is Agent Client Protocol... ...good?

It just looks to me like a bolted-on dongle to the past 50 years of kludges in editor design. It hasn't got 1/20th of the value proposition that a proper shared state layer would offer.

Re: Claude Code: Now in Beta in Zed

#404

Post by conartist6 »

Shank wrote: post #315
jryio wrote: post #149

What most of these comments are missing is the attempt at standardization and unification. There are a lot of comments that people need X feature in order to switch to Y editor. While that may be true and your particular workflow requires certain features, what is overlooked is the survival pressure for editors. It appears that our industry is moving towards adoption, sometimes mandatory, of AI coding agents. Regardl…

> I don't see why most editors should behave like hand crafted musical instruments when in reality they are much more akin to high quality knives in a kitchen (sure you have your favorite knife set and bring it from job to job, but at the end of the day you can be just as productive with a different knife when necessary). This is such a poor analogy. Yes, a good chef can make do with a different knife, but there is a…

As someone who is in the position to see what the next really disruptive innovation is, you're quite right that there exist much, much better ways to write and collaborate on code. Flying leaps of innovation to Zed's tiny shuffle-steps.

Re: Claude Code: Now in Beta in Zed

#405

Post by conartist6 »

conartist6 wrote: post #404
Shank wrote: post #315

Earlier quoted context omitted.

> I don't see why most editors should behave like hand crafted musical instruments when in reality they are much more akin to high quality knives in a kitchen (sure you have your favorite knife set and bring it from job to job, but at the end of the day you can be just as productive with a different knife when necessary). This is such a poor analogy. Yes, a good chef can make do with a different knife, but there is a…

As someone who is in the position to see what the next really disruptive innovation is, you're quite right that there exist much, much better ways to write and collaborate on code. Flying leaps of innovation to Zed's tiny shuffle-steps.

Zed spent their innovation budget on Rust and GPUI, and as a result they have no energy to question the status quo of IDEs as a whole. Git and LSP are antiquated but form the bedrock of their plans for the future.

Essentially at this point they can only do spaghetti enigneering: adding more and more complexity on top of the complexity that already exists. IDEs have been through so many iterations of this process already that all the real wins are in refactoring: moving the whole system (and ecosystem) design sideways, which is he one thing they dare not try to do (though it happens to be my forte).

Re: Claude Code: Now in Beta in Zed

#406

Post by tempaccount420 »

ramon156 wrote: post #372
kar1181 wrote: post #367

Also love Zed, but sigh, it's VC funded. We all know how this is going to end. Best VIM mode ever implemented in a (non vim) app. I use it as my 2nd editor (most of the time in Jetbrains products). I just hope I'm wrong about the medium term impact of the VC funding but rushing AI AI AI out seems to be a sign of that rather than fixing fundamental issues that remain such as the ugly font rendering.

Zed being OS is 100% what's keeping me from moving away. If anything happens you just fork it and accept it as-is

VS Code is also open source but a lot of Microsoft's extensions for it are closed source. I hope Zed won't go the same path.

Re: Claude Code: Now in Beta in Zed

#407

Post by benswift »

ppeetteerr wrote: post #141

I love Zed and I'm glad you now have native support for Claude. I previously ran it using the instructions in this post: https://benswift.me/blog/2025/07/23/running-claude-code-with... One thing that still suffers is AI autocomplete. While I tried Zed's own solution and supermaven (now part of Cursor), I still find Cursor's AI autocomplete and predictions much more accurate (even pulling up a file via search is more…

Glad it was helpful :)

I’ll keep an eye on this ‘proper’ Zed support for sure, although the current setup is working just fine so I might wait for v0.2.

Re: Claude Code: Now in Beta in Zed

#408

Post by danielbln »

beefsack wrote: post #388
manmal wrote: post #366

Earlier quoted context omitted.

Tbf I never use /compact but clear instead, and load in the relevant context anew. I just haven’t seen compacted context to be very useful, so far.

The model is usually so confused after a /compact I also prefer a /clear. I set up my directives to maintain a work log for all work that I do. I instruct Claude Code to maintain a full log of the conversation, all commands executed including results, all failures as well as successes, all learnings and discoveries, as well as a plan/task list including details of what's next. When context is getting full, I do a /cl…

The trick is to parametrize the /compact. Something like "/compact focus on the XZY, the next steps will be FOOBAR, and keep a high level summary of BARFOO"

That makes the compaction summary a lot more focused and useful.

edit: But a work log/PRD is essential regardless!

Post reply on HN