I've been a hardcore claude-4-sonnet + Cursor fan for a long time, but in the last 2 months my usage went through the roof. I started with the basic Cursor subscription, then upgraded to pro, until I hit usage limits again. Then I started using my own Claude API key but I was still paying ~70$ / 5 days, which is not that sustainable for me. But since grok-code-fast-1 landed, I've been using it daily with Cursor and it's fantastic, fast and cheap (free so far). I've also been using GPT-5 lately through the official Codex VSCode extension, and it blows my mind. Last night I used gpt-5-medium to help me heavily refactor a react-native app, improved it's structure and overall performance, something that would've taken me at least 2 days. Now I'm testing out gpt-5-medium-codex, asked it to restructure the entire app routing, and it seems it makes a lot of tool calls, understands, executes commands, it's very organized. Overall my stack from now on is Cursor + grok-code-fast-1 for daily use, and Codex/GPT when I need the brainz. Worth noting that I abused gpt-5-medium all day long yesterday, and I never hit any kind of limit (I just used by ChatGPT Plus account), reason for which I thank the OpenAI team
What exactly did your work flow look like for the gpt-5-medium refactor you did?
I don't have a test like that on hand so I'm really curious what all you prompted the model, what it suggested, and how much your knowledge as a SWE enabled that workflow.
I'd like a more concrete understanding if the mind blowing nature is attainable for any average SWE, an average Joe that tinkers, or only a top decile engineer.
I also hit Cursor usage limits for the first time in a year. Hit limits on Claude, GPT, and then it started using Grok :)
I chose to turn on Cursor's pay per usage within the Pro plan (so I paid $25, $20+$5 usage, instead of upgrading to $60/m) in order to keep using Claude because it's faster than Grok
I've landed on more or less the same. grok-code-fast-1 has been working well for most coding tasks. I use it in opencode (I guess it's free for some amount of time? Because I haven't added any grok keys ¯\_(ツ)_/¯)
How is this different from just using Cursor on my react-native codebase? Cursor in agent mode means: no copy paste, implements features and fixes errors iteratively, knows my codebase and adheres to existing patterns. If I need changes, I just ask Cursor and preview live app changes locally
Cursor is quite a bit better as well at not adding erroneous code. Was testing a0 and it kept getting stuck in endless loops of errors. I'm sure they'll improve but it's pretty rough right now.
We know Cursor is very good at code-gen and are improving our system to catch up. Our goal is to make the entire app development process faster and easier which involves alot of stuff outside of code-gen that we're working on and Cursor likely won't.
I would guess Replit-like (or Vercel-like) automation of aspects that are RN-specific. Eg typical mobile integrations, databases, more focus on UI (design screens with drag and drop + LLM chat), secrets. Focusing means they’re able to make features work better for just one type of developer, and can move faster. Cursor would need to solve for all types of development since their users probably do everything in all languages from web to mobile to backend etc.
Cursor is for programmers. Ultimately, you decide what the code should be.
v0/lovable/a0 will replace drag-and-drop "no-code" tools for non-programmers who don't care about code and only decide what the product should do. The tool will likely also manage hosting, either directly or through service providers, to ensure a seamless e2e experience, automatically fix runtime issues etc.
The question remains, will there be a need for Cursor and programmers in the future at all.
But keep in mind any point where programmers are obsolete is also the point where any job that can be done from a computer is obsolete. Including WYSIWYGing an app.
