Mithindon
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Is Human Control Safe?
According to the excerpt, Mithindon opens a LessWrong essay with a thought experiment: humans are a type of AI being assessed for safety, with their historical record of achievements and atrocities as test results. The essay appears to question whether humans, and so human control of AI, pass such a test.