[gwking]

I went from VS Code to Cursor, then got frustrated with Cursor breaking keybindings and other things, tried to go back to VS Code but missed the superior tab completion. Then I gave Zed a long hard try, but after over a month of daily usage I went back to Cursor again, just for the tab completion quality.

I don't use any of the chat or agent features, but for me Cursor's tab completion is a step forward in work efficiency that Zeta and Copilot were not. Sometimes it's subtle, and sometimes it is very obvious. Cursor seems to have sources of context that the others don't, like file names from the directory tree, and maybe even the relevant .pyi type annotations and docs for python modules. It also jumps to the next relevant problem site very effectively. It feels like the Cursor devs have done a ton of practical work that will be hard to match with anything other than a full-on competitive effort.

I want to see Zed succeed. I think it's very important that VS Code and its ultra-funded derivatives not dominate the modern editor landscape too thoroughly. Tab completion used to seem like a straightforward thing, but if the state of the art requires a very elaborate, whole-workspace-as-context environment to operate in, then I wonder if it's going to become a go big or go home kind of feature.

I can't help wonder what the actual internal API for this kind of thing is going to look like in the future. It used to be something like, what's the current token behind the cursor, and look in a big prefix tree of indexed words. Then maybe it got more elaborate with things like tree-sitter, like what's the incomplete parse tree up to this point. Then when editors started using AI, I stopped having any idea of what the actual inputs are. I'd love to hear about real implementation experience at any stage of this evolution.

[singhrac]

I think we don’t talk enough about tab completion model quality. Recently Copilot’s model got a lot better (probably trying to catch up to Cursor) but I feel like there’s still so much room here (and I assume Zeds is worse from your description).

Smart context / big context is a really interesting question, I’m kind of surprised Google isn’t building here given how much effort they’ve put into big context (they have Jules and Gemini CLI but no tab completion UX).

On further thought I think one of the big 3 (OpenAI, Google, Anthropic) should partner (ideally not buy) with Zed to get a foothold.

[dgunay]

For Copilot the quality of the tab complete is less of an issue for me than the fact that it is often very slow, or doesn't trigger at all when I would expect it to. I'll sit there feeling like an idiot for 10 seconds and then glance at the bottom bar to discover that it's not even doing inference, and have to randomly move the cursor, or delete and retype code until it finally works.

[the_duke]

I found Copilot tab completion completion to be VERY slow in Zed, for some reason.

It's fast in neovim.

Maybe they artificially slow down non-official clients somehow? (official neovim plugin, VS Code)

[the_duke]

I have the opposite experience, tab completion by Copilot just got significantly worse for me recently (the last week or so), both for Rust and Python code.

[kevmo314]

I've been working on a better tab completion model that stays as an extension: https://ninetyfive.gg/

The main feature I really care about is low latency, which is my main gripe about Copilot. There's still a ways to go to match Cursor's quality but I'm chipping away at it!

[dingdingdang]

Good work dude! It's way more functional to integrate the overall ecosystem rather than re-forking vscode ad infinitum!

[dkersten]

I went slightly differently:

I used Zed for about a year and a half exclusively, without using any AI features, and then switched to cursor to try AI features out. When Zed released its agent mode, I switched back to Zed.

I absolutely agree that Cursor’s tab completion is far superior to Zeds. The difference is night and day. Cursor’s really is that good. But the Zed agent mode works very well for me and Zed is, IMHO just so much better than an editor. I really hate having to use vscode or a vscode-based editor after using Zed so much (I used vscode exclusively before switching to Zed). And that’s enough for me to give up on the superior tab completion.

I hope Zed eventually improve theirs to a similar experience to cursor, but regardless, I love Zed.

[madacol]

nah, I've been using zed exclusively for a couple of months and Zed's agent mode is still worse than Cursor's, but I do agree the quality gap is smaller than on tab completion

[tripplyons]

I'm in a very similar position, using Cursor just for their Tab model. My ideal choice would be Neovim, but I can't replicate the productivity I have with Cursor Tab.

[hombre_fatal]

The tab completion is the only thing that keeps me on Cursor.

I never cared for the LLM sidebar.

But the tab completion is basically mind-reading.

[hollowturtle]

Same. I wish there was an option for enabling just tab completion and disable everything else

[Myrmornis]

You can hide all sidebars in vscode and you don't have to use any AI chat features.

[atonse]

I’m in the exact same situation. Prefer Zed’s snappiness overall but the tab completion in cursor is the only reason I keep coming back.

But at the same time, I’m also doing more vibe coding instead of manual coding as time goes on, so Zed might eventually win out.

[blurbleblurble]

What kind of configuration did you use for tab completion? Did you try hooking up different LLMs?

[gwking]

I paid for a subscription to both cursor and zed, without configuring any different LLMs or other options as far as I recall.