Unsafe choices in a two-player AI-race experiment were driven more by the opponent's actions and by falling behind than by the level of risk or individual risk preferences.
hub
Title resolution pending
1 Pith paper cite this work, alongside 1,887 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1,887
external citations · OpenAlex
hub tools
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Falling Behind Drives Unsafe Development in an Idealised AI Race Experiment
Unsafe choices in a two-player AI-race experiment were driven more by the opponent's actions and by falling behind than by the level of risk or individual risk preferences.