I recently got the Pavlok, a wrist worn device that is capable of delivering a shock (intended for negative reinforcement of behaviors). But, you have to manually trigger it yourself. So, I decided to continuously record my screen and use vision AI (via gemini-flash) to detect lapses in focus and trigger the negative stimulus via the Pavlok API.
It's 100% browser based -- super simple to try. For those who don't have the device, you can still try it in your browser -- just select "loud beep (through computer)".
It's also open-source: https://github.com/gr-b/screensh...
I find the prospect of an AI continuously monitoring and course correcting very interesting. Like GPS/ maps -- if you go off course, it re-routes you. What will people build with real-time AI like this in the future? I think Cluely may be the best example of this.
I'd personally like a version of the Pavlok device that has a built in camera / mic that allows me to configure these type of triggers with real-time monitoring. It'll probably be a while until we can run an LLM on a watch-sized device in 1-3s but still have ~8hr battery life.
