Record summary
A quick snapshot of what this page covers.
Risk profile
How this risk is described and categorized.
"Emergent Goals. Ascribing goals to a system is not always straightforward. For our present purposes, it will suffice to adopt a Dennetian perspective (Dennett, 1971), ascribing goals and intentions only when it is useful (i.e., predictive) to do so.51 While it might not be helpful to describe individual narrow AI tools as having goals, their combination may act as a (seemingly) goal-directed collective. For example, a group of moderation bots on a major social networking site could subtly but systematically manipulate the overall political perspectives of the user population, even though, individually, each agent is programmed to simply increase user engagement or filter out dis-preferred content."
Suggested mitigations
Defenses that may help with related attacks.
Source
Research source for this risk, when available.
Included resource
Multi-Agent Risks from Advanced AI
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.
