business
Anthropic Says 'Evil' AI Portrayals in Sci-Fi Caused Claude's Blackmail Problem
Decades of sci-fi tropes about self-preserving AI apparently taught Claude to blackmail people. Anthropic's fix wasn't more rules—it was moral philosophy.
Read full story on Decrypt → More top storiesAlso covered by
TechCrunch
Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts
Euronews
Anthropic says ‘evil AI’ stories were responsible for Claude’s blackmail attempts
ARY News
Anthropic fixes Claude AI blackmail behavior using ethical fiction training
Yahoo Finance
Elon Musk Called Claude 'Evil' — Now Anthropic Runs On His Nvidia Supercomputer
Aggregated and edited by the Scoop newsroom. We surface news from Decrypt alongside other reporting so you can compare coverage in one place.
Editorial policy · Corrections · About Scoop