Live data from Hacker News

Parallel agents in Zed

zed.dev

151–160 of 178 posts

Re: Parallel agents in Zed

#151

I personally explicitly avoid parallel agents, since it creates too much cognitive debt, and sometimes an agent may need steering towards an architectally sane solution mid-work.

Totally agree, the more parallel agents you spawn the more the probability of you vibe coding rather than guide coding. There comes a point when my mind says just commit and move on, which I fight to not do it.

Re: Parallel agents in Zed

#152

The new default layout is exactly backwards of what I want. It should go: project tree | text editor | agent view | threads Not to mention on most laptops you'll only have room for about two panes at a time. So they should be focusing on pane management and making it easy to swap between views. Not highlighting 4 pane workflows. Unless you have an ultra-wide monitor, I'd rather have a separate Agents window. I use Ze…

If they drop VI support, they lose me as a contributor and a user. It's the reason I started using Zed to begin with.

I don't think they'll drop it anytime, though.

Re: Parallel agents in Zed

#153

Zed is probably the best text editor in the last 10 years. It has quirks, but it is insanely powerful and capable out of the box. I don't even bother trying to setup Neovim because of Zed. They let people for PRs for missing vim features for their vim emulation, and its insanely capable. I hope someday they get the funding they deserve, because it has insane potential. It's why I subscribe to their pay plan, even if…

I do wish they'd focus on closing the gap to Jetbrains by implementing the QOL features that are missing. I understand they have to do what VC wants to see, but this agentic stuff is so tiring.

Yeah, Zed is why next year I might not renew with JetBrains at all. They hiked their price for AI stuff I didn't really ask for, especially when Claude Code does everything I want and need.

Re: Parallel agents in Zed

#154
Zed’s agent ui is the most confusing ui I have ever seen. Tiny and vague icons, clicking on ‘x’ sometimes closes the editor, sometimes an agent and sometimes a panel, hard to figure out what it will do. I wanted to try zed with new features but this unpredictable behaviour made me uninstall it. It also doesn’t support opencode Go which I am subscribed to.

Re: Parallel agents in Zed

#155
post #85
post #82

Earlier quoted context omitted.

I'm expecting we'll likely end back up on agents making PRs, and having to review them. Either that or giving up on quality etc/dealing with very messy code. I've been trying various automated testing/linting/etc strategies, and they only work so well.

That would be a nightmare. One thing is to review a PR generated by a human using AI and caring about the code; another is reviewing wild agents, especially when they make changes everywhere

Why? The vast majority of PR tools let you comment on specific lines of code, which you can't do with a prompt text area. The PR UI is superior over the standard agent UI.

Re: Parallel agents in Zed

#156

What are parallel agents worth to professional engineers if reviewing the code is a pain (aka non existent) in Zed? Please add proper code review tools (compare with branch|file|revision) and GH pr review tools like IntelliJ!

Zed doesn't even let you jump to the code that the agent is trying to edit. You have to search for the code yourself. It's incredibly annoying.

Re: Parallel agents in Zed

#157

The new default layout is exactly backwards of what I want. It should go: project tree | text editor | agent view | threads Not to mention on most laptops you'll only have room for about two panes at a time. So they should be focusing on pane management and making it easy to swap between views. Not highlighting 4 pane workflows. Unless you have an ultra-wide monitor, I'd rather have a separate Agents window. I use Ze…

> How long until they decide editing itself isn't worth it anymore? Stop supporting VI mode?

That seems like a leap.

Re: Parallel agents in Zed

#158
post #61

I would love to unleash parallel agents, but I am still checking every single edit while enforcing minimal, stateless, modular code, and I have the AI check in with me before writing the next file. A lot of times, I find it has incredibly stupid ideas and tends to make the code very messy. I would love to figure out how to stop that from happening automatically. The upside of checking in on the code, though, is that…

> I would love to figure out how to stop that from happening automatically. AGENTS.md

By all means elaborate. I can't imagine "don't have stupid ideas or write messy code" is going to make much difference.

Re: Parallel agents in Zed

#159

I like Zed but the defaults for tabs (CTRL+Tab and CTRL+Shift+Tab step you through some diabolical tab selector in what is allegedly (but not really) recency order instead of just left/right. It really made me question their sanity.

AFK right now, but IIRC there's a setting to control the ordering.

Re: Parallel agents in Zed

#160

Earlier quoted context omitted.

> I would love to figure out how to stop that from happening automatically. AGENTS.md

By all means elaborate. I can't imagine "don't have stupid ideas or write messy code" is going to make much difference.

To elaborate: That advice isn’t as objective as you think.

What one developer calls clean the other calls messy.

My advice is to use it, then document the issues when it gets messy. It takes some time, but no more than recruiting, training, paying another engineer.

Post reply on HN