MIT AI Risk Repository · Additional evidence · 68.03.00a

Sudden loss of control

Open the MIT Risk Navigator All entries from Chin2025

Description

"This risk is primarily based on two key ideas: the orthogonality thesis [118], [119] and the instrumental convergence thesis [120], [121]. Together, these theories argue that a superintelligent AI, regardless of its original goals, would develop power-seeking tendencies as a means to achieve those goals. However, arguments for this scenario typically do not spell out the concrete physical pathways an existential catastrophe would be realized. Instead, they argue that it is the default outcome given the eventual creation of a superintelligence based on a set of reasonable assumptions."

From Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks (Chin2025), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

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

Other entries from Chin2025

CBRN Risk Category · 4.2
CBRN Additional evidence
CBRN Additional evidence
CBRN Additional evidence
Cyber offense Risk Category · 4.2
Cyber offense Additional evidence
Cyber offense Additional evidence
Cyber offense Additional evidence
Sudden loss of control Risk Category · 7.1
Sudden loss of control Additional evidence
Sudden loss of control Additional evidence
Sudden loss of control Additional evidence