Hacker News Reader

Comment by jackjeff | Hacker News Reader

Is there some kind of alternative to Cursor in these terms

- fast because the code is already indexed no need to start every prompt rediscovering the world with rg

- in editor/vscode review much better than relying on git diff at the very end. You can click on next button to jump there. Quick edit in place. Or a quick prompt (seconds) to fix something small

- in editor completion / quick edits, when you do things by hand.

It seems that everyone loves agentic Claude code things these days but I don’t understand how you can review what it did and remain as much in the flow as you do with cursor.

Also I find that incredibly slow. By the time Claude finished a prompt I could have done a few in cursor.

And mind you, I’ve been wanting to use zed instead but the clunky vscode fork called cursor. But cursor has just a better UX for AI integration even though it’s slow and guzzle up RAM.

View on HN

> It seems that everyone loves agentic Claude code things these days but I don’t understand how you can review what it did and remain as much in the flow as you do with cursor.

The way I review it is to let it finish a PR sized slice and then I review the whole diff in a separate terminal as if it’s a PR from someone else. Then I very impolitely list the shit that needs fixing, let the LLM grind out a new batch and repeat the process. When the code is good enough I throw it into a commit and push a PR out for other humans to review.

Clicking around in a UI would just waste time and if the change is too large to review in a terminal window the change is too large for another human to review.

Considering the amount of rejects I do every single day I'm not sure I agree. Now that I cannot reject I am unable to do any agentic coding anymore.

You’re reviewing at the wrong layer if you’re approving / rejecting each individual tool call that modifies source code.

Look at the finished piece of work and then treat the agent as if it’s that colleague you really hate and nitpick the shit out of the change it wrote. Usually the agent writes some over-engineered garbage which you then “help it” whittle down to something you would be okay approving if another human wrote it.

There is a step missing. Impolitely list what's wrong and try to incorporate any persistent themes into a markdown file so that the agent stops making the same mistakes. Put any rules into linters and static analysis and sanitizers and ...

I sometimes see people reviewing LLM code leaving the same review comments multiple times, or worse, after some time they just give up reviewing.

Yep, if you’re not building guardrails, using an LLM is effectively just gambling until you get a non-broken output.

I 100% agree on the automated guardrails.

The part where you add instructions into a document is a bit of hit and miss. If they’re general enough it works but at my employer they have gone all out and have LLMs writing instructions that are committed to repos. There’s also a bunch of tools enforcing security instructions that usually just make the model confused (it starts arguing against the instructions randomly in the middle of performing a task). The agents are “stuttering” on most tasks because of the bloated instructions.

Yeah, workflows like ruff then ruff --fix are ideal, or just outright banning certain libraries, or having policies like dependency cool downs.

It's funny because we're once again speed running what the best practices already are!

>The way I review it is to let it finish a PR sized slice and then I review the whole diff in a separate terminal as if it’s a PR from someone else.

Insanely inefficient. It's 10x more productive to watch the thinking traces and edits in real time and steer the model appropriately.

If your workflow is typical no wonder my team members who use claude code are so much less productive.

Do you never have agents working on multiple tasks in parallel? You'll become much more productive when you figure out how to stop micromanaging.

More productive in what way? Letting agents burn tokens to produce garbage output is not productive. And letting teammates read code that wasn't reviewed by a human submitting it also isn't productive.

If I work with one agent / few subagents on one feature I can steer it as soon as I notice it drifting into the direction of waste. This way I only review the total diff 1.5-2 times. And I also don't waste my own mental energy on context switching between tasks agents are producing diffs for in parallel.

> And letting teammates read code that wasn't reviewed by a human submitting it also isn't productive.

If that’s what you got from my comment then you need to review it again.

I don't think this is something anyone who has ever read a "thinking trace" would unironically say. Not that you can even see them in Claude.

When thinking first started and you would still see the whole "thinking process", I thought it was a ploy to 10x token use because it was just the most inane bullshit. "But wait, the user is asking me to" in loops.

You can see thinking summary transcripts in Claude Code and Desktop, and they are actually useful because they don't have those sort of thinking loops from the raw tokens.

Exactly, looking at a few of these traces is enough to realise that it's a waste of time to read them. A friend once described it as like reading a fever dream, which seems fitting. They're a necessary crutch for how the tools work, but probably should be considered an internal state representation that only sometimes accidentally seems to make sense.

Wasn't there a study recently that even found a model's performance was sometimes better when the "reasoning" was nonsense? As in, no clear correllation between what the reasoning says in a human's interpretation, and how the model actually did with the task.

I sometimes read the traces out of boredom or morbid curiosity. My favourite bit with Claude is how, even if you give a very comprehensive prompt in complete sentences, almost every trace will contain a variation of "the user asks me to X, but their thought cuts off mid-sentence."

Fever dream.

Vs code copilot is the same or better than cursor in my opinion - I mean that's where cursor comes from

I just switched back to VS Code from Cursor a week ago. Things seem great and VS Code has caught up. Last time I tried switching back was in November and VS Code was not ready then.

Is this the chat on the side or the agents feature?

The chat on the side can use agents too

I code using Codex or sometimes ClaudeCode.

I use Zed to review the code.

CLI is great for most things. Some times, when I am reviewing a PR, I just tell Codex to do a diff between source and target branches in PR, and generate a HTML report. Then I read that, and also review relevant pieces of code in Zed.

I tried using Cursor, many of my colleagues use it, but stopped using it due to clunkiness. And of late, even in there, many of my colleagues use agentic coding. Instead, I prefer the snapiness of CLI (Codex coded in rust, takes less memory per session) and Zed (also coded in rust,) and blazingly fast. Zed is the new Sublime Text if you will.

Thanks your your feedback.

I just retried Zed and yeah, it's much much better than last time I gave it a shot!!!

I turned on the review stuff, and yeah I can do more or less what I could in Cursor. Check something. Do a quick inline promtp for the three lines I dislike and move on.

And of course the editor is so much nimbler/nicer.

No plan mode, but for big edits I'd probably use codex or something just like you. If you have any advice for integrating for that flow, I'll take them.

I guess whatever advantage cursor has, it will die once "Sol" is no longer integrated, as it was my favorite heavy work model. But I sure will miss the snappy auto/composer stack of Cursor.

If you integrate Zed with Claude Code through ACP you get plan mode (and some other stuff like memory)

Cursor's Grok models are a powerhouse without much of a performance hit.

Zed still has a lot of rough edges. A month or two ago I couldn't believe that a basic feature like code folding was just completely broken.

I love VSCode built in LLM harness. No extensions, use any model you want, amazing UX for reviews, control of agents. The sandboxing also seems great, I never see models touching anything they shouldn't.

Is this the chat on the side or the agents feature?

Both are great, and analogous to Cursor which has both features too.

I have to admit I'm not clear the difference? It starts with the list of your sessions/agents . Then starting a new "agent" or question or plan. I usually use each agent for a few questions or prompts at most. Occasionally it runs longer than that.

I love using it for the chat question style where I ask it things like:

For these frontend pages with X options collect the database tables for each.

This is of course something easy to do manually, but I like it stepping through a couple functions much faster than me searching around manually and maybe getting lazy and not checking all of them.

Claude / Codex ex tensions inside of VSCode give you what you described. I ageee, I find people that use only the CLI barely read and review the code the agent creates until it's too late

Lately I've been developing in Dart/Flutter. I use Android Studio but I know developers who use Antigravity and like it.

For the past three or four months it's performed very well, even the cheaper Gemini models. No serious complaints. But if you go back a year it was pretty terrible. My work style is to keep the coding agent on a short leash so YMMV.

Cursor no longer indexes your codebase.

Oh. Really? I guess that was not such an advantage after all… still cursor fast models are so much faster than what you get in Claude/codex.

Assuming there is an index, agent still needs to write queries against the index to get any information from it - might as well grep!

Do you know when they stopped and why?

EDIT - AI says:

Cursor seems to have intentionally dropped semantic/embedding-based codebase indexing. Their explanation is that newer coding agents are now good enough at searching repos directly. They can grep in parallel, inspect directories, read likely files, and refine the search themselves. Cursor says this now works as well or better for most cases. [1]

So the architecture shifted from something like “chunk → embed → vector DB → retrieve” to “local search index/ripgrep → agent explores.” There is still an index, but it’s a conventional local search index. No embeddings are involved in that retrieval path. [1]

The interesting part is that Cursor was still reporting a ~12.5% accuracy gain from semantic indexing in January 2026. [2] So this looks less like “semantic search never worked” and more like agentic search improving fast enough that the extra infrastructure stopped being worth it.

[1] https://forum.cursor.com/t/what-do-you-think-about-cursor-re...

[2] https://cursor.com/blog/secure-codebase-indexing

Interesting to see someone else is in the same boat as I am. Regarding editor review I agree, surely the solution would be to `git diff` at the end, but if you only want to git diff what was literally just changed by the agent it means you'd have to commit as you go so that your git diffs are more localised. And then at the end of your work just squash the commits. But it feels annoying. (EDIT: ok I forgot about git staging, that seems to be better)

I mainly use Cursor for another reason though: all of my work is remote over SSH and I don't like keystroke latency, so I prefer code editing / agent conversations to feel local. (Everything else is done in the terminal.) But I would also prefer to use something less propriety. I may go back to VSCode with plugins to achieve a similar experience.

Seems you're looking for an editor with agent, not just a agent, so something like Zed?

I do like Zed as an editor and I keep trying it out

but the the review what the AI did by jumping directly into the file with accept/reject/go next/next file with the ability to edit in place was nowhere near as good in zed vs cursor last I checked.

I recently cancelled Cursor.

The features you mention are in Antigravity IDE v1, which I am trying as I still have a Gemini subscription.

No idea how long it will be around for, as Google Antigravity2 (more like Claude Code) is clearly the favoured way forward, plus the new Antigravity for VSCode Extension*, which I didn’t like as much when I tried it. It offers the same accept/reject hunk workflow, but I don’t know about editing in place. It doesn’t feel as if it has the tight integration of Antigravity IDE v1, which feels as if it was designed to challenge Cursor.

Having said that, much of the time I use Google Antigravity2 alongside a Jetbrains IDE. You can still review all diffs within Google Antigravity2 and attach comments to any line on order for a followup prompt to make amendments. But I still prefer the review and accept/reject hunk workflow.

* https://marketplace.visualstudio.com/items?itemName=Google.g...

Thanks for the feedback. I’ve been trying to cancel my cursor subscription but I always come back. ;)

You’re welcome…

There are things I will probably miss from Cursor, as they used to iterate on DX goodies quite quickly. For frontend tasks, I liked the idea of Cursor Browser being able to do a devtools-like selection of an element tree to be included in the chat context. I’ve been told there are similar extensions available for vanilla VSCode, so will have to see how good they are.

They improve super fast though, releasing a new version every week. If you have specific improvements in mind open an issue on their github.

How does Zed compare to the tab completion in Cursor ("Cursor-tab")? It's honestly the only reason I have stuck with cursor in spite of the UI/UX being worse every single time I update it. Can I get something equivalent or better from Zed or some vscode fork/extension now? Admittedly I haven't looked in a bit, but it's seemed like nobody really cared about this workflow when I've tried in the past.

I haven't used cursor, but tab completion in zed works great for me. I also use it with Claude code extensively.

Also: the ability to draft a plan and monitor its execution, review it, and merge it from a cell phone. I know Claude remote is a thing, but it’s not the same.

This is a big quality of life thing. Sure, I should just go on a walk without having an agent going, but oftentimes it’s not intruding on it - it’s the thing that actually ENABLES it.

> I don’t understand how you can review what it did and remain as much in the flow

Separate terminal tab with git diff/show, Zed for edits - rarely, there is little reason to change code yourself. Opus at low effort is faster than you can switch windows.

OpenCode IDE + Serena MCP (for the indexing part)

[1] https://opencode.ai/

[2] https://github.com/oraios/serena

May be opencode2 in the near future. Sample (not affiliated) ~ 1. download opencode2 2. settings > tabs > vertical 3. add worktree setup to agents.md 4. use /diff to review changes 5. use commands for commit, sync and push

I don’t see how opencode 2 (or 1) addresses any of my concerns. I thought it might avoid rg/grep the code base on every prompt but does not even seem to be the case.

how is index superior to rg ?

What's wrong with using VSCode with your model / API key of choice?

Price?

I met the founder of Voidleap (https://voidleap.com) yesterday! They have been building a new type of code editor since early this year and has been dogfooding it themselves.

I haven't tried it yet but it looks promising. He would be thrilled if people give it a go!

I don't like being that guy, but wow, the AI slop copy on that website is so terrible, it's almost impossible to read. Every other sentence means absolutely nothing.

Slop website indicates vibe-coded software, and I wouldn't let anything like that even look at my code.

Looking forward to trying this out: https://zed.dev/blog/introducing-delta

Have you tried https://pyor.review ?

It’s not an editor in that sense but a tool optimized for reviewing PRs produced by AI.

Have you tried the continuity plugin to VSCode? I think it’s still rg‘ING the source but you get control over AI edits / review and quick own edits.

Will give it a try. Thanks!

Interesting that people aren’t suggesting smaller projects here - roo code, traycer are two worth checking out for this.

Codex

I use codex all the time. It’s inferior to cursor for the two reasons mentioned. It rediscovers the world with rg (no indexing). Wall of diff at the end.

The GUI slightly better than Claude. And it’s a million times cheaper than Claude.

Check out JetBrains Air

Interesting. Will check. Thanks!

It is so buggy every time I try to use it, even with Jetbrains AI it bugs out. I want to love it though.

Yeah it’s pretty new but they’ll get there. I was using IntelliJ and basically wasn’t using it as an IDE. Then I tried Air and I was like “they get it”. But yeah they have work to do to get it out of preview. They are very responsive though

I use zed

I used zed with codex for the accept / reject code review feature without relying on git but yesterday the Read Only drop-down disappeared and while I was doing my code review the AI agent started vibe coding without my permission. I hate this industry.

There's OpenCode, Claude Code, Codex. I don't like to use GUIs so I rely purely on agentic AI on CLIs.

In the case of TUIs I’m going to assume you review the code externally in neovim or lazy git or something like that?

I don’t like relying on GIT for that and making things as good/done as I go. But with these agentic tools that’s what I have to do. Stage everything I like, manually edits a few bits.

But what do you when you find something where you want to say the agent: I don’t like this for reasons x and y redo as z. I’m like one shortcut away in context inside cursor to say that to my agent? You have to change tab in herdr and then what? Type the file name and line numbers? Is there a way to do this that does not seem very frustrating?

Also open code, codex, etc. super slow. They grep the code. Every. Single. Time. Cursor has a semantic index

I usually copy paste snippet or function name that is affected and comment it. similar like you would sit next to coworker and tried to say where he/she messed up. agent is able to get location correctly

I know this is change of context, but I have full screen terminal toggled with keyboard shortcut and with middle mouse paste (Linux) I do not have to move cursor anywhere

Thanks for the reply. That makes sense. It’s sort of what I do too when I use codex/claude/t3 code, but usually via GUI.

The in-editor context review is something that does not seem long for first world. Sadly. Maybe I’ll be forced to make a zed extension or something, maybe on top of jujustu…

I use git diff and ctrl+click the file+linenumber which opens my IDE. Works well enough. I use this macro here when there are a lot of changes:

  gdf() { git diff '*'$1'*'; }

  gdf fileName (doesn't need full file name)

  gdf folderName (all files in a folder)

Guake and Yakuake have this always-on-top terminal overlay mode which is really nice for this kind of workflow. Works exceptionally well with multiple workspaces I prefer one single big monitor with everything maximized and multiple workspaces.

iterm2 on mac also has a similar mode, but it is a bit finicky to set it up (it is really hidden in the settings).

I review them on VIM, I use Zed as well.

I was looking at CLI-only solutions a while ago and the best thing I found was to use something like revdiff: https://github.com/umputun/revdiff

For instance, in Claude Code you can have it bring up this TUI overlay after every edit it makes (it literally is an overlay, rather than a separate tab in your terminal) and you can annotate line-by-line anything you want changed or rejected. Then once you exit the overlay those suggestions are automatically piped back into the agent.

I tried a few of these TUI-based code annotators, and this one is by far the best. It also works for files not under version control.

I'm currently not using it as I also prefer something more akin to "text editor with agent built in", but I wanted to mention here in case you were curious.

Reply on news.ycombinator.com