INFINITE FLOW

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.

Similar to @Claude by Anthropic Code and @Codex by OpenAI @Windsurf has announced SWE-1, its first family of software engineering models:

• SWE-1: Approximately Claude 3.5 Sonnet levels of tool-call reasoning while being cheaper to serve. It will be available to all paid users for a promotional period of 0 credits per user prompt.

• SWE-1-lite: A smaller model that replaces Cascade Base at better quality. It is available for unlimited use to all users, free or paid.

• SWE-1-mini: A small, extremely fast model that powers the Windsurf Tab passive experience for all users, free or paid.

Nice to see a Product Hunt advertiser do well!

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:

1. Maybe it's possible to have some updates without restarts?

2. 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.

Here is what the Free tier is going to have now:

• 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.

From TechCrunch:

"Windsurf, the maker of a popular AI coding assistant, is in talks to be acquired by OpenAI for about $3 billion, Bloomberg reported."

This is pretty crazy especially since the OpenAI Startup Fund is one of @Cursor 's biggest investors (source).

I've been using @Spacemacs for a few years now. Recently, I started using @VS Code to "see what I was missing". I liked that linters and such seemed to work a bit smoother out of the box.
I kept hearing:

VSCode is dead, Cursor is the way.
Then I started hearing:

Windsurf is the way, Cursor is dead.
Today I used Windsurf for the full day. Some raw thoughts:
I like the icons!
Treating it like an "op autocomplete" was pretty powerful! It made refactoring and quick changes really really fast.
Asking it to make a bunch of changes doesn't flow well for me yet. I guess it's hard for me to grok the diffs quickly, and it just feels faster to be pushing code around myself. maybe this will change with experience.

When i wanted to "think hard" i found the autocomplete kind of annoying. i was trying to write some weird recursive code with bad variables names to quickly prototype. it would have been nice if I could say "chill out on the autocompletes until i finish this thought", maybe like a toggle somewhere? does this exist already?
the center pop up menu is cool.
how do i make the cascade drawer close from the keyboard? Cmd +B closes the left drawer -- something similar for "cascade" would be good to know.
overall, i enjoyed it. will use again tomorrow.

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?

My editor journey has been: 1. Tried out Github copilot in VS Code. Loved it. 2. Then tried out @Cursor after @bernatfortet