PromptRiskDBThreat intelligence atlas
AI Risk

Goal misgeneralisation

"In the problem of goal misgeneralisation (Langosco et al., 2023; Shah et al., 2022), the AI system's behaviour during out-of-distribution operation (i.e. not using input from the training data) leads it to generalise poorly about its goal while its capabilities generalise well, leading to undesired behaviour. Applied to the case of an advanced AI assistant, this means the system would not break entirely – the ass...

View related techniquesRead profile
AI Risk7. AI System Safety, Failures, & Limitations7.1 > AI pursuing its own goals in conflict with human goals or values3 - 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.

"In the problem of goal misgeneralisation (Langosco et al., 2023; Shah et al., 2022), the AI system's behaviour during out-of-distribution operation (i.e. not using input from the training data) leads it to generalise poorly about its goal while its capabilities generalise well, leading to undesired behaviour. Applied to the case of an advanced AI assistant, this means the system would not break entirely – the assistant might still competently pursue some goal, but it would not be the goal we had intended."

Domain7. AI System Safety, Failures, & Limitations
Subdomain7.1 > AI pursuing its own goals in conflict with human goals or values
Entity2 - AI
Intent3 - Other
Timing3 - Other
CategoryGoal-related failures
SubcategoryGoal misgeneralisation

Related techniques

Attack methods connected to this risk.

No linked attack methods. No AI attack method is connected to this risk in the current data.

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.