Get the latest tech news

Anthropic wants to stop AI models from turning evil - here's how

Can a new approach to AI model training prevent systems from absorbing harmful data?

That said, President Donald Trump's recent AI Action Plan did mention the importance of interpretability -- or the ability to understand how models make decisions -- which persona vectors add to. Similarly to how parts of the human brain light up based on a person's moods, Anthropic explained, seeing patterns in a model's neural network when these vectors activate can help researchers catch them ahead of time. "Persona vectors are a promising tool for understanding why AI systems develop and express different behavioral characteristics, and for ensuring they remain aligned with human values," Anthropic noted.

Get the Android app