Wow excited for when Anthropic buys Cursor in a couple months and I get locked out of using OpenAI models with it. This is depressing. I just want stuff to work.
If LLMs were a sustainable business then Anthropic would have no problem selling Claude to a competitor. Heck they'd brag about it ("see OpenAI uses our models to code instead of their own!"). You see this in the industry all the time. Large tech companies compete with each other and sue each other and have deep business relationships at the same time.
What this change really says is that Anthropic doesn't want to burn VC money to help a competitor. And that is the reality of "I just want stuff to work". It won't just work because there's no stable business underneath it. Until that business can be found things will keep changing and get shittier.
Void is basically the same thing, but open source and better. It's easy to use with any provider API key, even LM Studio for local models. You can use it with free models available from OpenRouter to try it out, but the quality of output is just as dependent on the model as any other solution.
Have you used it? Haven't heard about it but tbh I can see how it would eventually outperform cursor and/or windsurf. As LLMS get better, and more background tasks etc, will come, I don't see a sustainably moat around IDEs generally (except switching cost, but if it is mostly vs code... )
saw you did below. What is your experience so far? fast requests are great. Anything big lacking?
I was using roo code for a bit and it was cool to see how fast it was going compared to windsurf.
I cancelled my Cursor subscription and haven't used it since. I experimented with Aider for a bit, it's also pretty great. Their architect mode seems to be the way of the future. It allows you to use a pricier model for its reasoning abilities, and it directs a cheaper model to make the code changes.
That said, I keep going back to Void because Aider's system prompts have a tendency to introduce problems. If Void had Aider's architect mode, it would be perfect.
Yeah, for sure. That's why I tried Cursor for a month. But as soon as I ran out of fast requests it became unusable. It had me waiting several minutes for the first token. I didn't realize how bad the experience was, fast requests included, until I used Void. It makes Cursor fast requests seem slow, and I tend to need fewer of them. The differences being that Void requests go straight to the provider instead of their own server first, and their system prompts seem to keep the models more on task.
That's fair. It is not the cheaper option, unless you use free or low cost models from a provider like OpenRouter. Of course, that comes with a performance hit. What I like about it is the flexibility. I run Devstral Small locally for easier tasks and it's free except for electricity. On the other hand, you can use up $20 with Gemini Pro in a couple hours with large contexts. Grok 3 mini has been a good middle ground- more capable than Devstral and less expensive than Gemini Pro.
So I tend to start with Devstral unless I know it will struggle, and then move on to paid models as needed. When I do switch to a paid provider, it's noticeably better than the same provider on a Cursor paid plan, so even though it's more expensive, I feel like there's more value there.
I honestly don't have a proper monthly tally yet. I've used $30 in OpenRouter credits over a couple weeks, but a lot of that was experimenting to compare quality of output.
Does anyone here actually use OpenAI models in Cursor? I kind of forgot they were even there. I've just been alternating between Claude and Gemini, and the sense I've had in online discussions is that that's pretty normal.
