PromptRiskDBThreat intelligence atlas

Self-improvement

AI Risk

"examples of cases where AI systems improve AI systems"

Overview

A source-backed snapshot of this AI risk.

Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Records2Source records unified into this concept.

Risk profile

How the MIT AI Risk Repository categorizes this risk.

Domain7. AI System Safety, Failures, & Limitations
Subdomain7.2 > AI possessing dangerous capabilities
Entity2 - AI
Intent1 - Intentional
Timing3 - Other
CategoryDangerous capabilities in AI systems; Capabilities that increase the likelihood of existential risk
SubcategorySelf-improvement

Merged risk records

Source records unified into this canonical risk concept.

2 recordsView all →

MITRISK-Maas2023-53.02.04 - Self-improvement

"examples of cases where AI systems improve AI systems"

Domain7. AI System Safety, Failures, & LimitationsSubdomain7.2 > AI possessing dangerous capabilitiesSourceAdvancing AI Governance: A Literature Review of Problems, Options, and ProposalsYear2023

MITRISK-GOS2023-56.19.05 - Self-improvement

Domain7. AI System Safety, Failures, & LimitationsSubdomain7.2 > AI possessing dangerous capabilitiesSourceFuture Risks of Frontier AIYear2023

Related techniques

Attack methods connected to this risk.

View all related techniques →
No linked attack methods. No AI attack method is connected to this risk in the current data.

Mitigations

Defenses that may help with related attacks.

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

Source evidence

Research source for this risk, when available.

View all sources →