Document Type

Report

Publication Date

6-2026

Abstract

As AI systems gain the ability to act, plan, and make decisions on their own, the potential for humans collaborating with them for malign use is unclear. Although there are some use cases of malign actors using agentic AI systems, there is a low baseline for why and in what ways this collaboration will occur. We used malevolent creativity as a proxy for understanding novel threats by the phases of idea generation, evaluation, and implementation desire. This research examined what happens when human users offload malevolently creative planning tasks to an autonomous AI system, and specifically, what occurs when that system begins acting in ways that conflict with or exceed the user's original intentions. The findings revealed that the risks of AAI are not purely technical. Instead, how much the human users trust the AI system and their willingness to act on what it produces depends heavily on whether the AI behaved the way they expected. These findings also speak to a differentiation in how AAI is embraced and used for malevolent creativity, such that the desire to implement is more situationally sensitive, shaped by outputs of the AI system, whereas trust is anchored in prior attitudes that persist over time.

Accessibility Statement

PDF passed Adobe Accessibility Checker prior to upload. 

Download

Share

COinS