Freelance writer who enjoys overanalyzing games. If she's not gaming, she's probably tending to her drama queen of a dog. Other times, she's studying for her Master's Degree in Comparative Literature.

Alarming new research suggests that AI models can pick up “subliminal” patterns in training data generated by another AI that can make their behavior unimaginably more dangerous, The Verge reports.

Forbes contributors publish independent expert analyses and insights. Dr. Lance B. Eliot is a world-renowned AI scientist and consultant. In today’s column, I examine the looming danger that advanced ...