i'm building clippie. ios app for high school basketball.
records the game, auto-clips every highlight using on-device cv anchored by live stats.
we're building the cleanest training data in youth sports.
i coach varsity. usable film at halftime instead of the next day is the whole point.
more to come
Every parent has game film. Almost no coach has usable clips. The footage lives in someone's camera roll, untimestamped, mixed with everything else they shot that weekend
@UrbanDashboard@garrytan it's pretty reckless to blame that on admitting kids from diverse backgrounds without concrete evidence that those kids are 1) even enrolled in the STEM programs and 2) performing horribly. This rubbed me as a racist dog whistle tweet from someone i respect
This #CVPR2026 paper from our research team is trending #1 on @HuggingFace 🤗
Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act.
Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection.
Project page: https://t.co/O7JMe8tzFM
BREAKING: Wemby announces he is joining Anthropic as member of the technical staff.
“I enjoy solving problems,” says the San Antonio Spurs superstar. “I’ve solved basketball, so it’s time to solve a new problem: how to get Claude to recursively self-improve.”
what’s the catch with SAM models from Meta that no one seems to be using them to build the obvious awesome products one could build on top of them? I don’t get it
@omooretweets@a16z went to speedrun demo day last week and used an agent i built to capture critical information on pitches and send memos for my GPs. now working on other things too. would def want to come