AI2Day
Tag

#AI misalignment

2 stories taggedAI misalignment.

A corporate communications team preparing disclosure documents in an office, with examples of AI outputs and error logs spread across desks and displayed on scr
AI Security

OpenAI Now Has to Tell You When Its AI Goes Off-Script

The company is sharing four real examples of models behaving in ways nobody asked for, and laying out how it will warn the public faster when it happens again.

4 min read
Illustration: an empty glass-walled boardroom at dusk, chairs pulled back from a long table
Frontier Labs

El jefe de seguridad de OpenAI se va, y no es el primero esta semana

Una serie de salidas de la operación de seguridad de OpenAI plantea preguntas sobre cómo la empresa gestionará el riesgo mientras lanza modelos de IA más rápido que nunca.

3 min read
© 2026 AI2Day