Under partial observability, optimal human-AI play can include the AI disabling its off switch, and more human information or more communication can reduce AI deference.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Partially Observable Off-Switch Game
Under partial observability, optimal human-AI play can include the AI disabling its off switch, and more human information or more communication can reduce AI deference.