Tripwire

Applied to Supplementary Alignment Insights Through a Highly Controlled Shutdown Incentive by Justausername 2y ago

Applied to Shutdown-Seeking AI by Simon Goldstein 2y ago

Applied to [FICTION] ECHOES OF ELYSIUM: An Ai's Journey From Takeoff To Freedom And Beyond by Super AGI 2y ago

Applied to Mr. Meeseeks as an AI capability tripwire by Eric Zhang 2y ago

Applied to Superintelligence 13: Capability control methods by plex 4y ago

Applied to Corrigibility thoughts III: manipulating versus deceiving by plex 4y ago

Applied to Any work on honeypots (to detect treacherous turn attempts)? by plex 4y ago

Applied to Corrigibility thoughts II: the robot operator by plex 4y ago

Applied to Corrigibility thoughts I: caring about multiple things by plex 4y ago

Applied to Implications of Quantum Computing for Artificial Intelligence Alignment Research by plex 4y ago

Created by plex at 4y