PromptRiskDBThreat intelligence atlas
AI Risk

Value specification

"How do we get an AGI to work towards the right goals? MIRI calls this value specification. Bostrom (2014) discusses this problem at length, ar- guing that it is much harder than one might naively think. Davis (2015) criticizes Bostrom’s argument, and Bensinger (2015) defends Bostrom against Davis’ criticism. Reward corruption, reward gaming, and negative side effects are subproblems of value specification highlig...

View related techniquesRead profile
AI Risk7. AI System Safety, Failures, & Limitations7.1 > AI pursuing its own goals in conflict with human goals or values2 - Post-deployment

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.

"How do we get an AGI to work towards the right goals? MIRI calls this value specification. Bostrom (2014) discusses this problem at length, ar- guing that it is much harder than one might naively think. Davis (2015) criticizes Bostrom’s argument, and Bensinger (2015) defends Bostrom against Davis’ criticism. Reward corruption, reward gaming, and negative side effects are subproblems of value specification highlighted in the DeepMind and OpenAI agendas."

Domain7. AI System Safety, Failures, & Limitations
Subdomain7.1 > AI pursuing its own goals in conflict with human goals or values
Entity1 - Human
Intent3 - Other
Timing2 - Post-deployment
CategoryValue specification
Subcategoryn/a

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.