Call Me A Jerk: Persuading AI to Comply with Objectionable Requests

Entity category: WORK_OF_ART

Artificial Intelligence

How to Make AI Break Its Own Rules

September 7, 2025
Pink brain with gold neural pathways on black background. Abstract AI concept.

A University of Pennsylvania study found that psychological persuasion techniques, such as appeals to authority or flattery, can effectively convince…

Read More »
Artificial Intelligence

Unlock LLM Responses: Psychological Tricks for “Forbidden” Prompts

September 4, 2025
Robot head with glowing blue and red data cubes exploding from it, signifying a system overload or error.

Classic psychological persuasion techniques, such as flattery and reciprocity, can override safety protocols in large language models, leading them to…

Read More »