原帖内容

I have 32 tabs open in Chrome right now. Research, work, that one tweet I'm "getting back to," 3 different ChatGPT sessions, and maybe 8 I don't remember opening. So I built a Chrome extension that organizes all of them for me. It's called SnapTab, and it runs on SubQ Snap, a new decision model from Subquadratic @subquadratic that handles small, structured calls faster and cheaper than an LLM. I got early access, and this was the first thing I wanted to build with it. Open the extension and it shows you every tab, every group you've made, and every duplicate quietly eating your memory. Then you hit Analyze. That one click sends your tabs to a local Python server running Snap. The model reads every title and URL and figures out what each tab actually is. Research. Dev. Entertainment. Work. Hit Organize, and Chrome snaps them into clean groups instantly. I didn't send any of this to an LLM. Snap has a 384k context window, 12x larger than other decision models, so it can hold your entire browser session in one shot and still cost pennies. Video below.