There's a lot of options for models these days. I've been using Claude 3.7 but I'm curious what's been working well for others. What model are you using and why?
Is the thinking version of @Claude by Anthropic worth the extra credit spend? Does @DeepSeek work well enough to save some credits? Is it worth trying any of the @ChatGPT by OpenAI models?
Windsurf is an IDE that enables anyone to collaborate in lockstep with AI. Built by the Codeium team, the Windsurf Editor combines the best of copilot and agent systems to help you ship products faster, leveraging better context to provide better suggestions.
The modern coding superpower. State-of-the-art suggestions on 30+ languages in your IDE: VSCode, JetBrains, Vim/Neovim, Emacs, and uniquely as a Chrome extension, enabling it on notebooks (Jupyter, Colab, etc), websites like JSFiddle, and web IDEs like Gitpod.
Dear @Windsurf, I appreciate the frequent updates. Love seeing a fast moving product. But, the restart-to-update is pretty brutal. There are like 3 updates per week.
I have long running processes in the editor terminal like my development server and rails console. When I restart the editor, I have to manually restart these processes. Some ideas:
Maybe it's possible to have some updates without restarts?
Can you indicate when my local major or minor version is behind the latest? I am no longer willing to restart the editor for most patch updates.
More premium credits: We are bringing all premium models to the Free plan with the full agentic experience. Instead of just 5 premium prompt credits a month, a user will get 25. With GPT-4.1 and o4-mini still on a discounted 0.25 credit rate, this corresponds to 100 such prompts every month.
Unlimited full agent: We are also going to give unlimited Cascade Base model usage in Write mode to our Free users. Previously, unlimited Cascade Base was available, but not with the full agentic experience.
Unlimited Fast Tab: Free users will now have unlimited fast Tab completions, the highest performing Tab experience that was previously available only to paying users. This is the full Tab experience - autocomplete, supercomplete, tab-to-jump, tab-to-import, and more.
Previews and Deploys: Unlimited Previews and one Deploy a day.
Introducing our new family of models: SWE-1, SWE-1-lite, and SWE-1-mini. Based on internal evals, it has performance nearing that of frontier models from the foundation labs.
