Record summary
A quick snapshot of what this page covers.
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)."
Suggested mitigations
Defenses that may help with related attacks.
Source
Research source for this risk, when available.
Included resource
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.
