Live data from Hacker News

Claude Code: Now in Beta in Zed

zed.dev

191–200 of 431 posts

Re: Claude Code: Now in Beta in Zed

#191
post #100

> Credit balance is too low I have a subscription to Claude. What gives?

When you run Claude Code it lets you pick between API key and Claude subscription login. It sounds like it found an API key in your env and is trying to use that. You may have to find a way to trigger a login to get you into your subscription account.

Yep, that was it. I had an Anthropic API Key set in Zed. Resetting that (after typing /login in the agent window) did the trick!

Re: Claude Code: Now in Beta in Zed

#192

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…

I'll third this. AI autocomplete is THE most efficient and helpful feature of Cursor, not the agents.

Re: Claude Code: Now in Beta in Zed

#193

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…

I was somewhat surprised to find that Zed still doesn't have a way to add your own local autocomplete AI using something like Ollama. Something like Qwen 2.5 coder at a tiny 1.5b parameters will work just fine for the stuff that I want. It runs fast and works when I'm between internet connections too.

I'd also like to see a company like Zed allow me to buy a license of their autocomplete AI model to run locally rather than renting and running it on their servers.

I'd also pay for something in the 10-15b parameter range that used more limited training data focused almost entirely on programming documentation and books along with professional business writing. Something with the coding knowledge of Qwen Coder combined with the professionalism and predictability of IBM Granite 3. I'd pay quite a lot for such an agent (especially if it got updates every couple of months that worked in new documentation, bugfixes, github threads, etc to keep the answers up-to-date).

Re: Claude Code: Now in Beta in Zed

#194
post #63

Earlier quoted context omitted.

Just disable it. It seems like they've made is as simple as possible to do so while also being realistic about what it takes to make a successful (read: profitable) IDE the year 2025.

I've found that the sort of people who complain about AI or cryptocurrency don't care if it can be disabled. The mere fact that such functionality exists taints the product for them. I can't say I understand the reasons (I like AI functionality), but that's what I've noticed.

I do care that it can be disabled. My problem with such functionality is that it becomes the sole focus of the development team, drifting their attention away from improving core experiences, such as language and plugin support, polishing ergonomics, and pruning papercuts.

Re: Claude Code: Now in Beta in Zed

#195
post #63

Earlier quoted context omitted.

I've found that the sort of people who complain about AI or cryptocurrency don't care if it can be disabled. The mere fact that such functionality exists taints the product for them. I can't say I understand the reasons (I like AI functionality), but that's what I've noticed.

I do care that it can be disabled. My problem with such functionality is that it becomes the sole focus of the development team, drifting their attention away from improving core experiences, such as language and plugin support, polishing ergonomics, and pruning papercuts.

The focus of the team is gone. Their target now is not to make a great product, but to make an engaging product that makes money however they can.

The AI is a symptom of the problem. If it weren't AI, it would be something else.

Re: Claude Code: Now in Beta in Zed

#197
post #102

My main issue with claude code is running multiple ones in parallel. I don't want to manually do all the git worktree stuff, I just want claude to handle it for me. So if Zed automatically handles that (where there's a worktree per thread) I can see the appeal. Apart from that, I'm already using Tower to view the changes so I'm not really sure what the value here is. I tried installing it, and got an error "can't loa…

I suspect Zed will aim to tackle this issue via DeltaDB:

https://zed.dev/blog/sequoia-backs-zed#introducing-deltadb-o...

Re: Claude Code: Now in Beta in Zed

#198

I like Zed in concept. I like Zed in the architectural and foundational aspects. I want more tools like Zed to exist. But, I find Zed challenging to adopt due to random nuances. First, settings management is a mixed bag and sometimes I just want a quick way to open the "settings.json" from the settings pane without fussing around. Then I'd like the "settings.json" to stay open (reopen) on a restart of Zed. Then I'd l…

For what it's worth, I think Zed now has a default keybind to open settings.json: Ctrl+,

I assume that keybind is also configurable?

Re: Claude Code: Now in Beta in Zed

#199

Earlier quoted context omitted.

I love how we just reinvent the wheel again, and again, and again, and again... MacOS native apps have had great sub-pixel rendering all along, but I guess since we have to develop everything in Electron now it's time to reimplement all the exiting functionality.

> MacOS native apps have had great sub-pixel rendering all along Apple removed subpixel anti-aliasing in Mojave, seven years ago, because it's not necessary on the HiDPI/Retina displays they ship as standard. They still do greyscale anti-aliasing but that's not the same thing as subpixel. Discussion from the time: https://news.ycombinator.com/item?id=17476873

> because it's not necessary on the HiDPI/Retina displays they ship as standard.

I disagree. Subpixel anti-aliasing triples the available horizontal resolution, and makes text crisper. The algorithms are known and regardless of the density it should always be applied to text and vector graphics elements.

The RGB stripe layout is so useful that OLED manufacturers are moving to it in 2026, away from the long-derided PenTile where magenta/green fringing is seen even on the densest displays.

In fact rendering on macOS is completely broken, and I don't know how people stand by it. At any scaling factor selected that is not a perfect factor of the actual hardware resolution (the 'looks like' value in Settings), the final framebuffer is scaled and interpolated to the display resolution, and everything is noticeably more blurry.

Windows has had some form of hardware-independent rendering since Windows 7, and proper pixel density control arrived in Windows 8.

Re: Claude Code: Now in Beta in Zed

#200

I want to try Zed but the Helix mode seems quite young. Vim mode sounds good, but i just can't move away from Helix mode. (oh and of course, my own modifications to Helix's input config) My difficulty in finding editors that fit my desired input scheme kinda reminds me of the old pre-LSP days. Where you'd chose an editor based on it's language features. I wonder if we need some sort of common editor interface to allo…

I agree, I've fantasized about an editor with a truly pluggable editing model which is decoupled from the other parts.

Yi was kind of designed like this, I believe. You could compile in an emacs-like model, a vim-like model, or presumably make your own model.

I've used Helix and Kakoune in addition to Emacs and Vim, but dealing with the limitations/featureset/plugin treadmill gets a little tiring.

I have been following Zed, and it seems that they have rearchitected things to enable adding Helix mode and making the editing model a bit more modular, but it's still fairly new. They are fixing bugs pretty quickly. I will have to try it again.

They have a nice discussion here:

https://github.com/zed-industries/zed/discussions/6447

They reference Ki, which also looks cool, and they out some of Helix's inconsistencies in their comparison: https://ki-editor.github.io/ki-editor/docs/comparisons/

I prefered Kakoune to Helix (it was more consistent). But to your point, being able to swap these things out more easily would let you choose an editor based on features, and not tradeoff between features and an ergonomic editing model.

Ironically you can use Ki inside of VSCode (and I know you can use Vim that way too), but VSCode is so darn bloated and slow...

Post reply on HN