EVERYONE "just use their mental skills to justify whatever conclusions they arrived at NOT using these skills".

You can't reason without starting from axioms accepted for some other reason. And nobody really knows what their axioms are. This is all a matter of degrees. Some people's conscious thoughts are more consistent than others...and that's about as far as you can justify. (But I tend to think more highly of those that agree with me.)

We can bust on Microsoft all day and all night, and they deserve it, but the fact that their ability to find and fix these problems has greatly increased is a good thing. Software is incredibly complex, and no software more complicated than "10 GOTO 10" is free from the potential of security problems. Microsoft's QA has gone downhill in recent years, but now it's getting better apparently (even if it's after the fact). They are not going away, so this makes all our lives better.

I think a better answer would be for everyone to use the same time number, and adjust their hours of operation to fit local standards. For this I pick Zulu time for purely historic reasons, though it's really no better than any other arbitrary choice. And scrap leap seconds. Every once in awhile you might have a leap minute...either that or use leap microseconds as needed once/year...say at the spring equinox.

Yeah, let 6:00 AM be defined as the local sunrise time! (I live shaded by a hill at astronomic sunrise.)

Well, I really think running everything on Zulu (Greenwich) time makes more sense. The number you put on the time is arbitrary. It's not like schools consider the schedules of the parents anyway, and everything that's automated runs 24 hours/day.

Well, time zones make sense unless you want to run everything on Zulu (Greenwich) time...which would have some advantages.

You're being silly. If the time is stable, then you'll set your hours to what it is. There's nothing special about the time number "10:00 AM". Businesses could have summer and winter hours if they chose to...at one time that wasn't uncommon.

Well, I can think of some uses if it were actually up to the job. I'd often like to have it read something to me, but it would need to be able to understand the emotional background.
E.g.:
Strange thing are done neath the midnight sun by the men who moil for gold,
The arctic trails have their secret tales that would make your blood run cold,
(etc.)

Or possibly have it read me The Lord of the Rings. And I have some fond memories of the radio program "X minus one".

But I *really* doubt that current AIs are up to that.

You don't have to like the forecast to track it against the news reports. (Of course, the news reports are often just PR, and you need to weigh that in.)

I wrote a file searching utility in C++ about 30 years ago. About 15 years ago I ported it to Python and found it to be faster than using the Windows directory enumeration APIs, and I've been using that ever since. It just searches filenames, but that's all I need.

"NOTE: Experiences vary by region." says to me that Microsoft doesn't even know what their changes will do.

The brainstem is probably rather invariant between people. That's an area where differences are likely to be fatal.

Actually, we're pretty sure it CAN happen by random chance. The argument is about how small that chance is...and what environmental conditions give the highest probability. And in what order things happened. (Currently I, not really knowledgeable in the field, think metabolism probably came before centralized information storage.)

YES!!
And *part* of the reason it's tricky is that we've got no real idea of what current AIs are going to develop into. Projections are all over the map.

FWIW, I tend to consider the AI2027 projections as identifying the most probably sequence, but there are lots of others, and none of them have any chance of being more than approximately correct. (The AI2027 people say it isn't moving quite as fast as they projected, but when I compare what they said against the news I'm not sure I believe them.)