This sort of nonsense is well studied in aeronautical world, and will lead to too many alerts, which, in turn, lead to predictable outcomes: https://flightsafety.org/asw-article/normalization-of-devian...

▲

ajross 4 hours ago | parent [-]

Very different threat model though. Commercial aircraft aren't sensitive to keep-your-eyes-on-the-road failures with seconds-scale latencies, airlines require autopilot use, there is a copilot present at all times, the FAA very strictly regulates work hours and substance use, etc...

Sure, don't nag a pilot who is already very well backstopped by the existing solutions. Your uncle coming back from the bar at 2am doesn't have any of that.

▲

dmitrygr 43 minutes ago | parent [-]

Repeated nuisance alarms have the same effect on all humans, not just on pilots - it trains them to ignore the alarms. Eventually this will lead to non-nuisance alarms being ignored and lives being lost.

	▲	ajross 3 minutes ago \| parent [-]
		That depends on "repeated" and "nuisance". My experience in a Tesla is that the attention monitoring never has false positive alarms at all. And it 100% has caught situations where I'm head down in the cockpit on autopilot in ways that, honestly, I probably shouldn't have been. So there's a single data point saying you're wrong. This kind of counter-intuitive/smarter-than-the-obvious pontification is a HN smell to me. Most of the time the obvious solution is correct. Driver attention management is one of the biggest (maybe the biggest) contributors to accident rate, and IMHO probably deserves some assistive technology attention. If the reverse is true, it needs actual evidence and not an attempt to reason from aviation evidence (a regime where inattention is NOT a major problem!).