News for hackers. Stuff that matters.
Re:ML is not that good at predicting consumers' choices by foobarian on Thursday July 21, 2022 @05:28PM (#32185351)
Well, the main selling point when it came out was that it was the iPhone of thermostats. It was the only thermostat at the time that did not have a terrible UI cobbled together by communist residential block designers or people who think that setting your own IRQ pins with jumpers is fun. But yeah I never understood the point of the learning feature; maybe a checkbox that needed to be ticked or a founder's pet feature.
Re:ML is not that good at predicting consumers' choices by avereveard on Thursday July 21, 2022 @11:20PM (#32188100)
It's mostly to trick people in thinking they don't need as many sensors for a smart home, once the nest is bought the sunk cost fallacy kicks in.