MIT AI Risk Repository · Additional evidence · 47.02.15.b

Nascent capabilities (emergent capabilities)

Category: Ethical and social risks

Open the MIT Risk Navigator All entries from G'sell2024

On this page 3 sections

Description

Example: "Strategic planning: Generative AI models have the ability to formulate and implement strategies to achieve the objectives set by their developers or users.440 They may devise strategies to accomplish intermediate goals that can divert from the developer’s intentions and the intended outcome.441 As a result, they may use unexpected and possibly harmful methods to achieve a goal"

From Regulating under Uncertainty: Governance Options for Generative AI (G'sell2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Domain: —
Subdomain: —
Causal entity: —
Intent: —
Timing: —

Other entries from G'sell2024

Technical and operational risks Risk Category · 7.3
Technical vulnerabilities (Robustness - unexpected behaviour) Risk Sub-Category · 7.3
Technical vulnerabilities (Robustness - unexpected behaviour) Additional evidence
Technical vulnerabilities (Robustness - vulnerability to jailbreaking Risk Sub-Category · 2.2
Technical vulnerabilities (Robustness - vulnerability to jailbreaking Additional evidence
Technical vulnerabilities (The risk of misalignment) Risk Sub-Category · 7.1
Technical vulnerabilities (The risk of misalignment) Additional evidence
Factually incorrect content (inaccuracies and fabricated sources) Risk Sub-Category · 3.1
Factually incorrect content (inaccuracies and fabricated sources) Additional evidence
Opacity (the black box problem) Risk Sub-Category · 7.4
Opacity (industry opacity) Risk Sub-Category · 6.4
Opacity (industry opacity) Additional evidence