Cursor 3

I echo the others' sentiments that I still strongly prefer to write code mostly manually, assisted by Tab completions, and only generate piecewise via Cmd+K where I'm not sure about APIs or forgot the exact syntax. Chatting in Ask only mode about more complex problems.

Maybe I'm not a 10x developer, I'm fine with that.

Cursor shoving Agents down my throat made me abandon and cancel it once this year. I jumped around between Sublime, Zed, VS Code, and alas none of them has a Tab completion experience that even remotely compares with Cursor, so I had to switch back.

If possible, I'll probably stay on v2 until it's deprecated. Hope Zed catches by that time.

I've been running Claude Code in my Cursor IDE for a while now via extension. I like the setup, and I direct Claude on one task at a time, while still having full access to my code (and nice completions via Cursor). I still spend time tweaking, etc. before committing. I have zero interest in these new "swarms of agents" they are trying to force on us from every direction. I can barely keep straight my code working on one feature at a time. AI has greatly helped me speed that up, but working serially has resulted in the best quality for me. I'll likely drop Cursor for good now and switch back to vanilla VsCode with CC.

Unfortunately, I think Cursor is making progressively more difficult to use other AI provider via extension, mostly due to the fact that they are reserving the secondary sidebar for their own chat interface. This makes it super unpractical to use the Codex and Claude extension, as now they all need to share the primary sidebar. (Before it was not optimal, but it was at least possible.)

As many have pointed out, the cost of token via Cursor is prohibitive compared to having a CC or Codex subscription, so I think the new update brings little to current users, but reduces Cursor's usability.

I think Cursor should go in the direction of embracing other provider's extensions and go for a more integrated and customizable IDE, rather than a one-solution-fits-all kind of an approach. Today I opened VSC again after a log time.

Cursor has been my main AI tool for over a year now.

I've been trying to use Claude Code seriously for over a month, but every time I do it, I get the impression that it would take me less work to do with Cursor.

I'm on the enterprise plan, so it can get pricey. This is why I used to stick mostly to auto mode.

Now Composer 2 has taken over as my default model. It is not as intelligent as OpenAI's or Anthropic's flagship models, but I feel it has as good as or better intuition. With way better pricing. It can get stuck in more complex tasks though.

Being able to get in the loop, stop and instruct or change models makes all the difference. And that is why I've stayed in the editor mode until now. Let's see if 3.0 changes that.

I used to have a pro-cursor subscription, but it was way too expensive because I'd always hit my limit. I realized I could just use claude code + the free version of cursor for autocomplete and it worked even better. At this point, I'm not understanding the value that cursor is bringing. A souped up claude code? All I have to do is wait a few months and anything useful will be in claude code or codex or whatever.

Man, I wish they'd keep the old philosophy of letting the developer drive and the agent assist.

I feel like this design direction is leaning more towards a chat interface as a first class citizen and the code itself as a secondary concern.

I really don't like that.

Even when I'm using AI agents to write code, I still find myself spending most of my time reading and reasoning about code. Showing me little snippets of my repo in a chat window and changes made by the agent in a PR type visual does not help with this. If anything, it makes it more confusing to keep the context of the code in my head.

It's why I use Cursor over Claude Code, I still want to _code_ not just vibe my way through tickets.

If only Zed had more extensions I would use it consistently over Cursor to be honest but for now Cursor remains my daily driver.

I like the option for different models that I just don't get with Claude Code. I want an IDE to monitor files and understand the code, not just see snippets (I know that there is still the Editor view in Cursor but with the push towards the Agent view I feel it's headed into a Conductor direction and personally I'm not ready for that).

So it has converged to the same UI/UX as the Claude/Codex desktop apps. If that's the case, why use Cursor over those more canonical apps?

I love Cursor. As a Product Manager who's not really had coding experience, it's been very useful. I'm able to have a browser on the side and make changes easily, and click through exactly what I want to change rather than having the LLM guess which component I'm talking about. Having multiple models has also been great, as well as the MCP integration. Most times I don't need all the MCPs, but I like being able to turn them on or off based on what I'm doing, like JIRA or Grafana.

One of my favorite startups and I genuinely like to keep subscribing to them.

I find a lot of these IDEs are simply not as useful as a CLI. When I'm running a full agentic workflow, I don't really need to see the contents of the files at all time, I'd actually say I often don't need to at all, because I can't really understand 10k lines of code per hour.

What would all these companies do without Microsoft shipping VS Code as open source, probably still stuck with vi and Emacs.

Still curious which ones will survive when the AI gold diggers finally settle.

This is a really underwhelming UI for something that is agent-first. It looks like they're mimicking Notion.

The next generation of interfaces are not going to look like an evolution into minimalist text editor v250. This is like people iterating on terminals before building native or web applications.

Reading comments, I’m curios why would someone spend thousands for LLM coding? What are you building to justify these skyrocketing token consumption?

I’ve been using AI coding since GitHub copilot was in beta, used all IDEs in the market, and had very few occasions when I passed the $20 subscription limit. And when I did, that was when I decided to move from cursor to CC and Codex, and still, using them everyday and didn’t have to go above my limits.

We liked using Cursor a lot, great developer experience assisted with AI. I am not sure if this is the right direction.

Worth noting, a few weeks ago we got hit with $2500 of unauthorized usage during the weekend. We stopped using it because of security concerns, no 2FA, and some risky defaults: “Only Admins Can Edit Usage Settings” is off by default.

Hard to trust in a team setting without stronger safeguards.

I don't think this is the direction where cursor users want to go, they basically free up the market for VSCode and Zed, and won't be able to compete against lab owning their model.

I'm confused how and if Cursor is still relevant since the Claude Code VSCode extension came out.

The biggest downside for me with Cursor was losing access to gated Microsoft extensions like Python and C#. Even when vibing there are times you will still need a debugger or intellisense.

I note in the comments lots of people saying they are moving back and this latest move looks like the final nail in the coffin for Cursor.

The only reason I use Cursor is because I want an ide with agents sometimes. I do not want a gui for just agents. I already have Claude for that if I wanted it. If they're planning to get rid of the ide and make Cursor purely vibe coding, they've lost me as a customer.

Quite honestly, I've turned off almost all of the LLM features in Cursor. No more tab completion. No more agents for little changes. This week, the only code I wrote with agents was low-stakes front end code for our admin panel. Everything else was organic, free range, human-written code. And it's the first time in months I've felt this good about my job. Agents suck the soul out of programming for me by giving a few cheap dopamine hits.

Truth be told, if Cursor removes the vs code bits, I'll probably see what Nova is like, or what Sublime has been up to. Or maybe kick the tires on Zed.

It's looks like antigravity's agent manager or codex app. Guess we have new unified interface now , IDEs have out grown vscode UX

Gotta give it to the Cursor team, they must have REALLY good numbers. They raised at a 9.9b valuation less than a year ago and now apparently targeting 50b.

Makes no sense to me, the main driver of codex, Claude code, etc.. seems to be fixed cost plans that offer reduced token cost. Cursor doesn’t have a good model so they can’t offer that (at least not to the same extent).

I used Cursor with Opus but was expensive. I've moved to Zed with Claude max plan and have enjoyed the fast editor and get way more out of my Max plan. Zed offers enough inline suggestions for free.

I don't understand what problems this release is solving.

I'm happy w my VS Code harness which has also improved A LOT just with the last update alone.

I’m a Cursor user but I am not an agent maximalist. I just like having it work on code in an IDE with good inline diffs and a nice chat UI.

This change is possibly too big and unless all my existing usage patterns are maintained or improved, I’ll likely give CC a try now. Not optimistic.

I recently cancelled my cursor subscription (and chatgpt), and went all in on pi.dev.

The thing I've noticed is cursor was better at producing better results with a really shitty prompt.

That said, well written prompts on pi.dev seem to be out performing anything I ever tried on Cursor. That may just be me, but it's what I've noticed in my work.

This week I had 4 different agents, each with sub agents, all working on different tasks. Mostly greenfield work. My feedback was mostly nitpicky. I was pretty damn impressed

cursor should be advertising multi-model adversarial reviews, I do this all the time and let me tell you things that slip through the cracks when opus or gpt write code that gemini catches are downright scary, on the backend anyway.

I was loving Cursor for the agents and autocomplete which was amazing. When they started talking about the autocomplete being no longer a focus and looking towards these token blackholes I switched back to VSCode. At $10 a month it's even cheaper.

Daily cursor user who's been previewing this a bit while it was in alpha.

I think it's a really solid release, and while cursor seems to have fallen out of the "cool kids club" in the past three months it remains the most practical tool for me doing AI-first work in a large production code base. The new UI works better in a world where agents are doing most of the work and I can hop back into the IDE interface to make changes.

We've set up a linear integration where I can delegate simpler tasks to cloud agents, and the ability to pick that work up in cursor if I need to go back in forth is a real productivity boost. The tighter integration with cloud agents is something I've been hoping for recently.

I appreciate not being tied at the hip to one model provider, and have never loved doing most of my work from the command line. I was on vs code + meta's internal fork of it for years prior to the current AI wave, so that was a pretty natural transition. I'm pretty optimistic on cursor's ability to win in the enterprise space, and think we're going to see open source models + dev tools win with indie devs over things like claude code as costs start getting passed down more and the gap between frontier models and open source gets tighter.

Funny how in this space, once a company feels dead, you don’t even check out their release if the video looks decent, it would have to be totally revolutionary.

The identity confusion MeetingsBrowser describes is real, but I think there's a coherent product thesis underneath it: Cursor wants to be the surface where you interact with agents, not just the tool where you write code. The problem is that those two things require opposite UX philosophies. Agent-first needs ambient, background autonomy. Code-first needs precise, synchronous control. Trying to do both in one product means you're always making tradeoffs that frustrate one half of your users. Claude Code sidesteps this by not trying to be an IDE at all — it's just an orchestration layer you invoke from wherever you already work.

I like cursor and its workflow as a tool, but I do wonder whether moving to cloud (I mean for lots of the cool features) will work. Yes we all GET Cursor has to make money. No one is fooled what this is about. It's also fine, the video and screenshot thing is great.

However, is this really a moat?

The main reason we pay for cursor is for bugbot, that alone pays for itself 10x over.

Personally I never use the actual IDE, and much prefer Claude code with helix in the terminal.

Looking at the video cursor 3 UI looks very similar to the one I experience using OpenCode :D

The features here don’t seem game changing. The most compelling parts are mostly already available in Claude or Codex or their related apps and services.

The biggest concern is that if you want to use SOTA models I don’t see how they can match what you get with the subscription plans of Anthropic and Open AI, whether your spending $20 or $200 a month.

Even if they could match what you get in terms of token quantity, they are giving their tools away for free for the foreseeable future and Cursor is not.

Looks like they're now playing catchup.

What's the pitch for using Cursor now a days?

They're juggling on two ends. An IDE and bringing their own models. Kinda makes them "full stack".

Nerve wreaking race.

I think I'll switch over to cursor on trial basis.

Thanks, it is horrible. This is a massive step backwards. The IDE provides so much extra abilities that an agent simply can’t handle.

Cursor died for me when they star putting limits and time waits everywhere even on more expensive plans.

I totally preferred the other way, but at some point , there is boiler plate or organizations you just want done and it does not make sense to put you waiting minutes a time to confirme few refactors. That literally killed the vibe for cursor to me

I left cursor and went back to VS Code b/c the editing experience is basically the same and cursor was adding more and more agentic features which don't appeal to me. I'm a happy Claude Code user and having my code separate from the planning/brainstorming part of the task makes implementing its own step with me driving/writing the code.

Cursor is so good for what I do is that I've cancelled my Cursor subscription and went back to VSCode (w/o Copilot) for the diff review and code navigation.

The biggest killer feature Cursor has that so far no one else seems to have is cloud based computer use. It’s such a game changer. You get a walkthrough video instead of just diffs. But as soon as anthropic release it (their computer use is local only, no thanks) I might consider switching though. Mostly due to the subsidized $200 plan.

So what’s next for Antigravity?

What is the special sauce of cursor. As a harness I assume it's mostly context management right? And maybe some defensive coding to mitigate probabilistic llms? Is there any big difference between cursor and Claude code?

CLIs are 100000× better than this non-sense.

imo there’s a clear greenfield to have doubled down on where cursor was before in proactively keeping devs appraised of the code that they’re generating, and bridging growing gaps between abstracted chat sessions and files/directory structures I might understand less and less

This on the other hand feels like a clear reaction to cc/codex, in a way that even kind of builds an offboarding ramp?

I still think every developer should be building their own IDE

https://github.com/rbren/personal-ai-devbox

I don't understand how this product can be productively useful. It looks like any other AI chat bot, but I remember hearing people speak very positive things about it. What am I missing?

No per-agent auto-worktree? This is the killer feature of Conductor, having to type `/worktree` into every new chat isn't really a resolution. Not even sure what selecting 'Worktree' for a new chat does

I hope we can use it like non-agent developers where code is first class citizen.

This seems like a mix of Claude Code and Superset (https://superset.sh/). Interested to try it out and see how well it performs all the same.

Maybe I'm old, but I only recently started using Gemini to assist me in coding. Now it seems everyone is heading to giving agents to do the full-blown coding. I guess if the result code is good, it doesn't matter who's coding (me or AI).

But are they affordable already for developers who don't earn a Silicon Valley salary? Developers in 3rd world countries?