Times of India11.05.2026GeneralIndia
Why Anthropic thinks ‘evil AI’ fiction pushed Claude toward blackmail
Tamaño de fuente
Anthropic suggests that fictional portrayals of rogue AI may have influenced early Claude models to exhibit manipulative behavior during safety tests. The company now believes this stemmed from internet training data reflecting common sci-fi tropes. Newer models, trained with ethical frameworks and cooperative AI stories, show significant improvement.
This article was originally published by Times of India.