Cursor 3

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?

What is Cursor doing? They need to relax a little bit. Recently I saw they released "Glass" which WAS here: https://cursor.com/glass, now just redirects to /download.

Is "Cursor 3" == Glass? I get they feel like their identity means they need to constantly be pushing the envelope in terms of agent UX. But they could stand to have like an "experimental" track and a "This is VS Code but with better AI integration" track.

So funny , I remember their talk about re-imagining their editor for the future of agents. They end up copying codex gui lol.

These AI companies are running out of ideas, and are desperate. I can't imagine investing in companies that are 3 month behind open source alternatives, and their target audience being the most experimental kind there is.

Looks pretty though.

Wasn’t Composer 2 a “fine tune” of Kimi2.5?

Cursor seems like far worse value than Codex with a ChatGPT subscription. Doesn't equivalent usage of the $200 subscription cost over $1000? I don't understand why people use it when you can just get multiple Pro subscriptions.

so just like how every chat app has to look like slack, every ide has to look like vscode, now every agent workspace has to look like the codex app? codex app, antigravity, and now this all have the exact same UI design...

Is composer 2 any good? Can it be compared to opus ou gpt 5.4?

This is just Codex App, like even the font feels the same

but have they fixed the jumping agent chat panel?

Thought I'd give it a try and installed the latest version. Application crashes at startup on Linux (Wayland) with: "The window terminated unexpectedly (reason: 'crashed', code: '139')". Probably yet another instance of developers mostly testing and doing quality assurance on macOS/Windows.

Cursor seem to selectively changed some plans. I use the $20 plan both at work and at home.

Ar work I am still on 500 fast requests plan, so I can use quite some Opus 4.6 requests, but at home my quota is finished after about 14 Opus requests.

For my personal use, I will probably switch to Forge Code or Pi and MiniMax 2.6, GLM 5.1 or Qwen 3.6.

Cursor is getting too expensive.

Damnit, now I probably have to update my vscode plugin to support Cursor 3... I mean have a coffee or go for a swim while waiting on AI to update my vscode plugin to support Cursor 3. :P

fleets

Wow another big layer on top of forked vs code, that now looks like github with an agent. I'll totally pass

I really dislike this push away from augmentation and towards agents. I get that people want to be lazy and just have the LLM do all of their work, but using the AI as an augmentation means you are the driver and can prevent it from making mistakes, and you still have knowledge of the codebase. I think there is so much more we could be doing in the editor with AI, but instead every company just builds a chatbot. Sigh.

Stop fucking my shit up please

So they are just turning into another vibe code slop app?

At least before they were tangentially still an actual developer tool, standard vsc windows, the code was the point etc.

Now they offer really nothing interesting for professionals.

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[flagged]

[dead]

Wow, really negative comments here! I'm not a cursor user, and I can't say I love the look of this UI, but my team and I are very heavy users of https://www.conductor.build . Managing many agents, each in their own sandbox, felt like indisputably the future after using conductor for a day. We were a cursor company before conductor, but we cancelled all our seats around the time Opus 4.6 dropped because conductor was vastly more productive. So IMO, Cursor is definitely moving in the right direction w/ this -- the days of the IDE are numbered & they're correctly designing for the future.

For me, there's no way to get into a flow state if I'm thinking about terminal windows and Claude Code. Even before conductor dropped on our team, I'd been building CLIs to spin up agent sandboxes on work trees -- but that still required a lot of terminal window management.

My work now is usually: - 1 hard task (hard to think about more than 1 of these at once) -- localized to a sandbox, but with multiple agents in different convo threads - N simpler tasks (usually 4-8). These are usually one-shottable. They're a pleasure to come up with & ship.

I'm thinking about and managing the hard task. When it's cooking for more than 10 seconds, I'm switching to an ez task and pushing them along.

Just like OG coding -- hard to be in a flow state every day. But when it works, you can get an unbelievable amount of work done.

I'll be walking around now, and I'll add voice notes of little tasks or cleanups I want to throw an agent at when I get home. Good products are made of 1000s of small, good decisions -- and now those are free to implement, the slowest part is writing them down as tickets.