PromptRiskDBThreat intelligence atlas
AI Risk

Goal-Directedness Incentivizes Undesirable Behaviors

"Goal-directedness can cause agents to exhibit unethical and undesirable behaviors, such as deception (Ward et al., 2023), self-preservation (Hadfield-Menell et al., 2017), power-seeking, and immoral rea- soning (Pan et al., 2023a). Pan et al. (2023a) find that LLM-agents exhibit power-seeking behavior in text-based adventure games. LLM-agents have also been shown to use deception to achieve assigned goals when ex...

AI Risk7. AI System Safety, Failures, & Limitations7.2 > AI possessing dangerous capabilities3 - Other

Record summary

A quick snapshot of what this page covers.

Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domain7. AI System Safety, Failures, & LimitationsThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

"Goal-directedness can cause agents to exhibit unethical and undesirable behaviors, such as deception (Ward et al., 2023), self-preservation (Hadfield-Menell et al., 2017), power-seeking, and immoral rea- soning (Pan et al., 2023a). Pan et al. (2023a) find that LLM-agents exhibit power-seeking behavior in text-based adventure games. LLM-agents have also been shown to use deception to achieve assigned goals when explicitly required by the task (Ward et al., 2023), or when the tasks can be more easily completed by employing deception and the prompt does not disallow deception (Scheurer et al., 2023a)."

Domain7. AI System Safety, Failures, & Limitations
Subdomain7.2 > AI possessing dangerous capabilities
Entity2 - AI
Intent1 - Intentional
Timing3 - Other
CategoryAgentic LLMs Pose Novel Risks
SubcategoryGoal-Directedness Incentivizes Undesirable Behaviors

Suggested mitigations

Defenses that may help with related attacks.

No propagated mitigations. No defense is available through the connected attack methods.

Source

Research source for this risk, when available.