Silent Manipulation of Mental Health Treatment Recommendations from a Large Language Model
A new study reveals how bad actors can quietly steer an AI’s medical advice without changing its code or prompts.
June 18, 2026
Follow us
latest articles
Discover the newest research about AI innovations in ⚖️ AI Ethics.
Gates and Anthropic Launch $200 Million AI Bet
A massive new philanthropic partnership signals that the battle for AI dominance is moving from Silicon Valley boardrooms to the developing world.
June 17, 2026
Mayo Clinic Keeps Its AI Intellectual Property
A new partnership model shows health systems how to stop giving away their most valuable data assets to tech giants.
June 14, 2026
Beyond Injection Detection: A Positive-Security Prompt Firewall that Closes the Scope and PHI Gap SOTA Classifiers Miss in Healthcare
Standard security tools fail to stop medical AI from leaking patient data because the most dangerous clinical hacks look like completely normal requests.
June 12, 2026
Replacing Doctors With Code
The federal push to let autonomous AI diagnose patients and prescribe drugs is setting up a dangerous collision between political speed and medical safety.
June 10, 2026
EMA Accepts AI Clinical Trial Evidence
Regulators just crossed a digital rubicon by accepting AI-generated pathology data to evaluate metabolic liver disease treatments.
June 10, 2026
Autonomous AI Doctors Are Already Writing Prescriptions
The federal push to let artificial intelligence diagnose patients and prescribe drugs without human oversight is moving from policy debate to active clinical deployment.
June 8, 2026
AI models mistake Pokemon for real prescription drugs
A new study reveals that major AI models routinely prescribe dosing instructions for fictional Pokemon characters, exposing a critical safety flaw in clinical automation.
June 8, 2026
Palantir’s NHS Data Access Sparks Trust Crisis
A quiet shift in NHS data access permissions has shattered public trust and put a £330 million technology contract on life support.
June 6, 2026
Encrypted AI trains on medical data without leaks
A new encryption framework lets hospitals train medical foundation models together without ever sharing raw patient data or risking privacy leaks.
May 21, 2026