Hacker News Reader

Comment by unsupp0rted | Hacker News Reader

What's the benefit of this compared to the IDE? To be more like Claude Code?

Flip your thinking around for a second and consider why an IDE is required for an agent that codes for you?

The IDE/editor is for me, the agent doesn't need it. That also means I am not forced to used whatever imperfect forked IDE the agent is implemented against.

> why an IDE is required for an agent that codes for you

Because the agents aren't yet good enough for a hands off experience. You have to continuously monitor what it does if you want a passable code base.

Sure, but monitoring, reviewing and steering does not really require modern IDEs in their current form. Also, I'm sure agents can benefit from parts of IDE functionality (navigation, static analysis, integration with build tools, codebase indexing, ...), but they sure don't need the UI. And without UI those parts can become simpler, more composable and more portable (being compatible with multiple agent tools). IMO another way to think about CLI agentic coding tools as of new form of IDEs.

As was already mentioned elsewhere, Emacs + Magit to monitor incoming changes is a great combo.

yes i am rejigging my whole vim setup

Following are now stars of my workflow

* Git plugins - Diffview, gitsigns, fugitive

* Claude Code plugin / Terminals with claude code

* Neovim sessions

* Git worktrees

Editing focused workflows have taken an backseat

* LSP

* Vim motion and editing efficiency

* File navigation

* Layouts

why even use vim at this point? the LLM ecosystem there is decent, but definitely less polished than using a modern IDE

Vim motions are nice.

I don't really need an IDE, but I do need a great code review interface.

As someone who hasn’t used Claude Code yet, can’t you configure it somehow to use a different tool of your liking, or it has to be in the cli?

I end up using the VCS tooling (lazygit for me), but coding agents really need to be integrated with this review environment. We need an extra step where the agent will group its changes into logical units (database models in one commit, types in another, business logic in another, tests in another), rather than having to review per-file.

Programming has changed from writing code to reviewing/QAing and reprompting, but the tooling hasn't yet caught up with that workflow. We need Gerrit for coding agents, basically.

I just merge the change and review the diff. If it’s wrong I either revert or ask Claude to fix it.

I use lazygit for that. But any diff tool you like will work.

Whenever I have to take the wheel myself the AI tab completion makes it much smoother so I am kind of addicted to that. Semi-automatic mode.

I would much rather use IntelliJ so perhaps my habits will change at some point, but right now I am stuck with Cursor/vscode for the tab completion.

Many of these companies are realizing that mainline VSCode is a moat of sorts. I and many people I know won't use any of these that require forking VSCode.

With the benefit that you can also pull in people who don't like using VSCode such as people who use Jetbrains or terminal based code editors.

Actually, I think where Claude Code shines, is with the VSCode Extension. It's a great mix between a CLI that could be used in a bash script for automation, as well as a coding assistant.

I haven't found however if Cursor cli provides this kind of extension

So you can use an IDE other than VS code.

I am so curious to know. Why is Cursor not just putting whatever this supposedly does better into... Cursor?

To compete with Claude code

They are competing with Claude Code already. The competition is not over who can built the nicest CLI.

They now compete in a larger market - non vscode users

i dont think it actually does anything better than the chat window in the editor. its strictly worse tbh. it just lets you not be tied to a VSCode interface for editing.im sure Jetbrains diehards would very much appreciate this, but honestly i will find it hard to utilize given the fact Cursor's tab auto-complete is so amazing.

You can spin up the Cursor CLI inside the terminal of your IDE of choice and not be tethered to Claude's models.

Is there a better agent than the anthropic one

Depends how you define "better". Quality/breadth of tasks/capabilities? Probably not (TBD how gpt5 will fare, colleagues were saying that it was better at some frontend tasks than claude4 in the alpha/beta horizon tests).

But if you take speed/availability/cost into account, there might be "better" offers out there. I did some tests w/ windsurf when they announced their swe1 and swe1-lite models, and the -lite could handle easy tasks pretty well. I also tested 4.1-mini and 4.1-nano. There are tasks that I could see them handle reliably enough to make sense (and they're fast, cheap and don't throttle you).

You can already use non-Anthropic models with Claude Code with tools like Claude Code Router [1].

[1]: https://github.com/musistudio/claude-code-router

Reply on news.ycombinator.com