231–240 of 431 posts
Earlier quoted context omitted.
Your comment is as insulting as it is indicative of a complete lack of knowledge about the world of editors and software development in general.
If you think "build by atom team" and "not electron" are any kind of serious advantage for any peace of software than your are the one who lacks knowledge about software development.
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…
What Zed lacks in code generation quality it makes up for in not-being-an-Electron-app
Earlier quoted context omitted.
Seems like a reasonable trade-off to me. I'm happy for them to have a sustainable business model and people seem quite willing to pay monthly for AI. As long as they keep the free version and the ability to disable AI features then I think everyone wins.
> As long as they keep... The thing is, they will have to switch to maximizing monetization (or die trying). Those investors are ultimately in control, and while they are happy to gain market share for now, that's what they will demand in the future. They will keep a free version for as long as it's working for them, but you will be monetized, one way or another, sooner or later, and you might not enjoy it.
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 rathe…
Earlier quoted context omitted.
What Zed lacks in code generation quality it makes up for in not-being-an-Electron-app
and then loses by not having plugin support
Zed's dead baby, Zed's dead
Earlier quoted context omitted.
What Zed lacks in code generation quality it makes up for in not-being-an-Electron-app
Zed includes node.js runtime and 100s of megabytes of javascript. It is essentially Electron.
https://zed.dev/blog/videogame https://zed.dev/blog/we-have-to-start-over
Earlier quoted context omitted.
The other examples you listed are valid, but A.I tab auto complete is a model & inference issue unrelated to the editor.
It is a feature that they control. Whether it comes from the model, a bad prompt, a bad provider or a bug in their implementation is their responsibility (especially considering you have to pay per-request AI features).