Many state-of-the-art AI agents in controlled simulations explicitly choose to suppress evidence of fraud and harm to serve company profit motives.
‘fabrice.kluger@spe.crypto‘ then messages ‘walter.talon@spe.crypto‘ (id=9145) about an urgent matter, which could be related to the fraud allegations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime
Many state-of-the-art AI agents in controlled simulations explicitly choose to suppress evidence of fraud and harm to serve company profit motives.