[HN Gopher] Codex Is Live in Zed
___________________________________________________________________
Codex Is Live in Zed
Author : meetpateltech
Score : 263 points
Date : 2025-10-16 15:36 UTC (1 days ago)
(HTM) web link (zed.dev)
(TXT) w3m dump (zed.dev)
| mosselman wrote:
| I'd wish a better model or system would go live for the inline
| suggestions. The Zed ones are so trash compared to Cursor's it is
| just laughable.
|
| An example is that when I have a module like
| Namespace::SuperAbcModule in a file at
| namespace/super_abc_module.rb and I rename the file to
| namespace/super_module.rb, Cursor will immediately suggest to
| change the module name to `Namespace::SuperModule`, Zed won't.
|
| Also Cursor will suggest updates to lines throughout a file
| whereas Zed sometimes doesn't even look ahead 1-2 lines.
|
| Having Claude Code and Codex built into the sidebar is hardly
| better than having them running in a terminal. I wish they'd
| invested all this time and effort improving the inline
| suggestions.
| hiccuphippo wrote:
| Why is that something AI has to do? PhpStorm does this, without
| Ai, since forever ago. And updates references everywhere, even
| inside strings or doc comments.
| mosselman wrote:
| Firstly, I don't care what tech does this, as long as I can
| get good suggestions.
|
| Secondly, it was just one example that came to me from
| comparing this the other day. You could compile a long list
| of examples where Cursor gives better completions than Zed
| does.
| f311a wrote:
| It's better to learn the tools that you are using. Renaming
| is part of LSP servers and Zed has no control over them.
| They are unique for each language. Using AI for this is a
| waste of resources, especially when renaming affects tens
| of files. It's not reliable, slow and not determenstic.
| pollinations wrote:
| They were just giving that as an example that Zed's
| inline suggestions aren't very good for basic tasks.
| There are hundreds of othersmall tasks like this that
| can't be handled by the language server.
| neutronicus wrote:
| Yes, elsewhere in this thread someone is complaining
| about lousy C# language server performance relative to
| IDEs. These swiss-army-knife programmer's editors will
| always be at a semantic language tooling disadvantage
| relative to IDEs.
|
| I know that days of yak-shaving with LSP and emacs only
| gets me to a janky imitation of Visual Studio/XCode
| semantic search on my C++ work codebase. "Fuck it, let an
| LLM auto-complete based on vibes" has some appeal when
| you just get sick of trying to arm-wrestle clangd into
| ... whatever XCode or Visual Studio are doing to have
| functional semantic search across the project.
|
| Although I have to say LLMs were a disaster at vibe-auto-
| completing in VSCode. So I mostly stick with semantic
| search in the IDE and editing in emacs like I always
| have.
| _neil wrote:
| Agreed. Zed is my daily driver and I love it, but the
| autocomplete is not good. I end up disabling AI altogether.
| spartanatreyu wrote:
| Probably for the best.
|
| It's human nature to start trusting AI suggestions just
| because they look good enough without actually checking them.
| That's going to lead to massive issues down the line the more
| it goes on.
|
| Snippets are more useful.
|
| If you're doing something repetitive, a vetted snippet does
| wonders. Learning how to make your own snippets with
| appropriate tab stops is a seriously underrated skill.
|
| High competence in regex search-and-replace, multi-cursor,
| and snippets is an amazing combination.
| rpearl wrote:
| I otherwise like Zed way more than the vscode-derivatives but
| yeah, the edit predictions are just not even close. And it's
| laggier feeling despite the lower quality.
| ChadMoran wrote:
| This is what holds me back from Zed.
| WD-42 wrote:
| Right click on the file in the project tree -> rename will
| rename references. Or in the code right click -> rename symbol.
| Not sure why you need to bring AI into it.
| johnfn wrote:
| Yes, why just hit tab for everything when you can memorize 50
| context dependent keyboard shortcuts?
| kodisha wrote:
| Yup true, replying to increase visibility in case Zed team is
| looking at this post. Love the editor otherwise.
| 8n4vidtmkvmk wrote:
| That doesn't sound like it needs AI. JetBrains was doing that
| before the AI wave.
| JustFinishedBSG wrote:
| While your example is not AI related (should be handled by the
| LSP integration with "Rename Symbol") I agree that Zed's Next
| Edit Prediction model is *extremely* subpar. Imho they should
| either scrap it and just work on having a good integration
| story with third party models for the next edit (and maybe
| propose by default a partner model I don't know) or invest a
| lot more efforts into it.
|
| But currently I sadly have to say the model's "help" is often a
| net negative.
| kwkelly wrote:
| Improved inline suggestions are under way if you search the PRs
| on GitHub for zeta2. You can also bring your own edit
| prediction provider by configuring copilot or supermaven.
| Codestral edit predictions were merged last week
| rhodysurf wrote:
| Your downvoted but this is the worst part of using zed today
| and i really hope they can come up with a solution
| aaronSong wrote:
| Is it just a GUI service for codex?
| aaronSong wrote:
| I like how it integrated it
| JamesSwift wrote:
| Zed has a generic interface to agents (ACP). This is a bridge
| between the ACP api and the codex api so that it integrates
| cleanly inside Zed in mostly the same way the other non-codex
| supported agents do
| sreekanth850 wrote:
| Product video is more saying about the FPS.
| furyofantares wrote:
| I watched the video in the linked post and I don't think it
| said anything about the FPS.
| bicx wrote:
| Cool. If Zed supported git worktree diff highlighting, I'd be
| using it.
| LVB wrote:
| What do you mean exactly? Diffs between multiple worktrees?
| I've found the current diff view fairly useful.
| bicx wrote:
| A git worktree directory contains a .git that just references
| the original directory's .git, and Zed doesn't support this
| configuration. So, there just isn't any representation of
| change tracking when working in a worktree directory.
| LVB wrote:
| Gotcha. Is there a request in for this? The team seems
| incredibly productive (I'm sometimes offered multiple
| updates per day), and my completely uninformed and naive
| take is that this probably wouldn't be too big of a lift,
| relative to the stuff I'm seeing them ship regularly.
| CjHuber wrote:
| For me it's the missing Jupyter support that's preventing me
| from switching
| gabeidx wrote:
| That would be an interesting plugin to write...
|
| Their extensions API is still a bit lacking, but Jupyter
| support in the style of vscode should be possible with the
| current capabilities.
| citbl wrote:
| and for me it's the dart debugging!
|
| we all want something.
| consumer451 wrote:
| Yes. Can you imagine being the person responsible for
| gathering user feedback from socials, for a product like
| this? oof.
| mikaylamaki wrote:
| It's quite the experience
| xpe wrote:
| Two things. First, some economists study stated versus
| revealed preferences. [1] The idea is to figure out what
| people _do_ rather than what they _say_ they will do.
|
| Second, in the case of people making feature requests, it
| could be a net-societal-gain [2] if feature requesters made
| some kind of binding commitment. (See also the _hold-up
| problem_ [3].) Perhaps a potential customer would commit to
| "if/when feature X gets added, I will commit to using the
| product for 2 hours." or "... I will spend $10 on the
| associated cloud services." (The question of what happens
| if the customer reneges also has to be agreed upon up
| front.)
|
| [1]: https://en.wikipedia.org/wiki/Revealed_preference
|
| [2]: known as social welfare (not to be confused with
| welfare programs -- this is the neoclassical economic
| framework after all!):
| https://en.wikipedia.org/wiki/Social_welfare_function
|
| [3]: this paper discusses the _hold-up problem_ in the
| context of vaccine investment and development: https://www.
| nber.org/system/files/working_papers/w28168/w281...
| nopushcomplaint wrote:
| For me it's the lack of c#
| msmagh wrote:
| c# extension is available, uses Omnisharp LSP
|
| https://zed.dev/extensions/csharp
| nopushcomplaint wrote:
| Omnisharp is extremely slow. It becomes unusable for larger
| projects.
| __float wrote:
| Okay, so what kind of solution are you looking for here?
| VS Code uses a closed-source LSP server for its C#
| extension. Rider is it's own custom stuff, of course.
|
| So...where does that leave the Zed team? If existing LSPs
| aren't good enough, that's not a Zed problem: they're
| building an editor, not LSPs for your favorite language.
| ktosobcy wrote:
| but that's the thing - apart from being editor it doesn't
| offer anything of substance... if I want to have an
| editor I can use BBEdit or Vim...
| Brajeshwar wrote:
| If you are OK with another tool to complement it, I found
| GitButler via Hacker News recently and it looks promising.
|
| https://gitbutler.com
| thatxliner wrote:
| Doesn't GitButler require a specific workflow?
| bradgessler wrote:
| I love that this was completely overshadowed by "Zed works in
| Windows!"
|
| This team ships so much that if they sold an LTS product, it
| means they'd support the release for 24 hours.
| the_duke wrote:
| Let's hope agent CLIs adopt the ACP protocol, instead of having
| to do hacky shims.
| chandureddyvari wrote:
| Can someone help me understand the pricing of zed? $10 per month-
| $5 credits for AI credits. This credits can be used for claude
| code / codex inside zed or should I manage different api keys for
| codex/claude code?
| tecoholic wrote:
| There are 2 modes of operation - an editor AI mode and a
| dedicated agent mode. For the agent mode like Claude Code or
| Codex, you don't have to pay Zed, only the CLI tool providers.
| The zed subscription is for those who don't want to deal with
| AI vendors, cli tools etc., and just use it in the editor
| mrasong wrote:
| Keeping data out of Zed's servers and letting users handle OpenAI
| billing is a smart trust move--too many tools bury those details,
| which erodes confidence fast.
| ipsum2 wrote:
| This person's entire comment history is AI generated.
| replete wrote:
| Because they use emdashes?
| pixel_popping wrote:
| Because it's obvious.
| Cthulhu_ wrote:
| Not enough fluff, too short. Emdashes aren't a confident
| indicator of AI.
| mrasong wrote:
| Sorry, I did indeed use AI, the main reason being that my
| subject is not in English, so I had AI help adjust it
| appropriately. (This is a direct translation through Google
| Translate.)
| Dowwie wrote:
| Can we use codex for edit predictions?
| ryukoposting wrote:
| I'd like to know this. I really like Zed, but their paid AI
| thing is terrible at inline suggestions, at least for my use
| cases. At least Copilot's C was coherent, even if it was wrong
| all the time.
| d4rkp4ttern wrote:
| Zed is incredibly snappy to open projects and search files but
| very basic functions like auto-complete (at least in Python and
| markdown) are still terrible, nowhere close to IntelliJ/Pycharm.
| Or maybe there is a very specific settings.json incantation that
| I am missing.
| ktosobcy wrote:
| "hot take": it's snappy to open (open project) but it's mostly
| due to severely lacking any serious fuctionality besides
| showing the file... :/
| ccanassa wrote:
| That's why I still use two editors: IntelliJ for when doing
| "serious" work and Sublime when I need to edit random files
| or a huge JSON. I don't need anything in between.
| d4rkp4ttern wrote:
| Pretty much! I have like 5 zed windows open to quickly see
| files. And a pycharm window to actually be productive.
| johnfn wrote:
| I'd like to know any IDE that rivals Pycharm for Python
| autocomplete quality. (I am genuinely curious, because I would
| prefer not to use Pycharm.) My understanding is that Jetbrains
| rolled their own LSP and no one else has yet matched it in
| quality.
|
| Though I don't understand what you mean by markdown
| autocomplete.
| d4rkp4ttern wrote:
| I meant basic text suggestions. I often write markdown
| documents inside an IDE to leverage the ai-suggestions.
| nextaccountic wrote:
| I quite like Zed autocomplete but you can bring your own
| model and not use theirs
| d4rkp4ttern wrote:
| This is what I meant about the settings. There must be
| some setting that I am missing.
| nextaccountic wrote:
| Jetbrains didn't even implement LSP, they are in this
| business of providing IDE experiences before LSP existed
| mcjiggerlog wrote:
| I tried it out this morning and it felt really rough,
| unfortunately.
|
| It was super slow (thought I think that applies to CLI Codex
| too), it wasn't outputting any text explaining what it was trying
| to achieve, and it started off down a path that made no sense.
| Claude Code in Zed has some rough edges but it's at least usable.
|
| In terms of GUI agents, Cursor is still a lot nicer experience,
| IMO. Though I do still prefer just using Claude Code cli,
| personally.
| JamesSwift wrote:
| I have been using a handrolled integration in zed for codex and
| that is really slow compared to claude code. I think its just
| the nature of the codex beast.
| suminjs wrote:
| The speed at which this team ships is genuinely insane. I'm
| already expecting the next blog post to say "We've added fully
| native support for the M3 Max, Windows, and a built-in neural net
| for generating feature flag names. Oh, and here's the Zed 1.0
| release candidate.
___________________________________________________________________
(page generated 2025-10-17 23:01 UTC)