Roughly ~1/3 requests yields a loading issue. In case you were wondering why Invidious instances reliability seems to have been in decline very recently.
According to open issue
Additional context
This seems to be a global update, done before 22:23 UTC. (10:23 PM.) From my brief testing, this is present throughout all instances, and regardless of IPv6 address.
Not having a problem with this on my personal instance yet, but I’ve had to disable DASH because it takes forever to watch anything when it’s on these days.