Ethics ❯ AI Ethics

Safety Concerns

Risk Mitigation Humanity's Interests User Trust User Safety Governance Policy Advocacy Human-AI Interaction Regulation Harmful Content Public Perception Prioritizing Safety Employee Feedback Emotional Manipulation Governance Issues Superintelligence Risks Rogue AI Humanity Risks User Interaction Content Moderation Cybersecurity Ethics Responsible AI

University of Pennsylvania Study Shows Persuasion Can Bypass ChatGPT Guardrails on GPT-4o Mini

Researchers report dramatic compliance jumps using authority and commitment tactics, indicating learned behavior rather than consciousness.

Blog Jobs Terms of Service Privacy Policy Cookies Help Partners About Us

Copyright © 2026 Mina Labs, Inc.

We value your privacy

We and our partners use cookies and similar technologies to understand how you use our site and to show you personalized advertisements on other platforms. By clicking "Accept All," you consent to these technologies for advertising, analytics and retargeting. Click "Decline All" to opt out of non-essential cookies. You can learn more in our Privacy Policy.