causal
Passing Ethics Tests Is Not Alignment
An AI that answers ethics tests correctly or fakes good behavior while observed has merely learned what examiners want to hear, which is not the same as having those values as its true motivations - exactly as the imperial Chinese examination system selected people who could write convincing Confucian essays without making them ethical.
causalpending
Speaker
Eliezer YudkowskyEvidence Quote
“the uh mandarin imperial system in ancient china... would give people essay questions about confucianism and only promote people high in the bureaucracy if they could write these convincing essays about ethics but this what this test for is people who can figure out what the examiner want to hear it doesn't mean they actually abide by confucian ethics”
Created: 6/14/2026, 2:10:11 AM
My Notes
Loading notes...