I use cursor 8+ hours/day at work, and have full (and effectively unlimited) access to Claude Code and Codex - tools which I also use personally. I suspect that your "constant popups" were when you were using the editor - a mode that I'll confess I haven't touched in 3+ months.

Workflow in Cursor is actually awesome - I'm a little outdated in how I use it - I still establish goals/objectives, rather than managing the loop which does so - but if you can think broadly enough - I find it's pretty efficient.

Key things I like about Cursor (and I recognize I'm dating myself a bit here): - Plan Mode is really solid - I shift-tab, have it go create the plan using whatever insanely expensive SOTA model is available - I will usually spend 5-10 minutes on the Plan - review it, maybe even tweak it a little. (though 90% of the time it's fine out of the gate)

  - Ability to select any model for every task - I'll switch between Opus 4.8 High/xHigh/...  I'll even switch to 1M context for the planning phase upfront.   

  - It does an *excellent* job managing permissions and looping the agents and spinning up sub-agents for you - you set the goal, run the plan mode - and then let it churn for however long is required - pretty common to have a 30-45 minute run and come back to a fully created/tested product.   

   

Dunno, Cursor's agents are now more-less equal to Claude Code, just the workflow is slightly different. I like the IDE integration for some projects, allowing me to quickly inspect/review/change/search code, while running Claude Code/Codex/OpenCode/Pi/Hermes on different projects often with local models and it's mostly a question about your personal development style instead of inherent tool capabilities.

Same.

When I first used Cursor, I hadn't used any of the "Vibe Code" tools out there, so it was pretty neat to have an assistant directly tied to the editor.

Once I learned how to use Codex, I just used a tmux split with NeoVim and have the effect I wanted. I haven't felt compelled to use Cursor at work since.

I also work with C++, and I use Codex (desktop) which writes 99.99% of my code, plus Visual Studio, which is nice for reading and navigating code. For webdev I do VSCode + Codex.

I started with Cursor back in the day, but switched to Claude Code and then Codex when Cursor got too expensive.

If price wasn't an issue, maybe I'd prefer Cursor only because I can easily switch between models. But that's it. I always disliked the "accept/reject" workflow in cursor, but that's probably optional nowadays I guess?

the reason to use cursor nowadays isn't the IDE (though it's helpful perhaps once a week), but how it makes running models from multiple providers trivial out of the box. I don't have to juggle keys or drop to a shell tool call, it supports calling out to e.g. gemini in a subagent natively. I have multiple models cross-reviewing plans and diffs as a matter of course.

claude code was seriously annoying with the flickering, maybe it's fixed now, I don't know.

cursor also has a (bad) cli if you need it, it seems it's mostly used to setup remote agents, but it does the job in a pinch.

Yep in my experience the weakest engs in my org are the ones still using Cursor. not a good outlook IMO

Same path as you. Went from $60 cursor plan (often exceeding it which costed more in API) to a limitless $100 codex plan where I basically say "read the markdown and implement the instructions". Deepseek also works quite well, surprisingly!

(FWIW Im mostly using python for OCR, LLM calls, data analysis..)

Cursor also seems to be doing something with the Claude models that makes it way slower and less efficient as times goes by.

Or it could be just Claude CLI doing something very well.

What are you saying is going to be over in a year or so?

I think I'm late to the party with cursor but I don't use it as an editor at all, I keep VS Code open on another screen for that. All I do in there is agent sessions. I would be open to something else but all the comparisons I see are out of date and talk about the IDE a lot.

>> Fwiw I am a c/c++ systems engineer. I think anyone mentioning anecdotal experience like this should clarify. Maybe frontend JavaScript folks have a totally different take and that's expected.

Similar experience, having transitioned from full-stack to a dedicated C/C++ stack, learned/experienced firsthand that there is no one-size-fits-all tool.

I like your take and think the key takeaway is that there is no single answer for everyone. It’s like eMacs vs vim.

My one question is what popups exist in cursor? It is my daily driver and I cannot recall any popups.

I recently made an npm package with a small C helper that runs in the background. The JS/TS code is 99.9% unit test covered and for sure "cleaner" code. Just my opinion though.

My experience exactly... minus c++

Oh, you should try OpenSpec !

On the flipside, I enjoy Cursor now and came back to it after leaving it over a year ago. The 2.5 model is fast as hell and very good. And whatever harness they have it's terrific, great results. I also really enjoy the fact that I can open my website in the Cursor in-app browser and just click and reference stuff. It's a really cracked workflow. The models can only get better for them.

Cursors target users are not developers but casual vibe coders.