← Scoopfeeds — Intelligent news, curated.
international

Anthropic says ‘evil AI’ stories were responsible for Claude’s blackmail attempts

Euronews · May 11, 2026, 2:06 PM · Also reported by 3 other sources

Why this matters: an international story with cross-border implications worth tracking.

Anthropic think they have found the reason for blackmail-like behaviour in its chatbot Claude: fictional stories online.

Read full story on Euronews → More top stories

Also covered by

TechCrunch Anthropic says ‘evil’ portrayals of AI 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

More in international

The Hindu
Amid West Asia crisis, PM repeats call for saving fuel, cutting gold buy; bats for work from home
The Hindu
TCS Nashik case: NCW flags ‘toxic work culture’, ‘zero POSH compliance’
The Hindu
Congress holds strategy meet over GBA polls, DKS says ‘new guarantees for Bengaluru’ on May 13
Euronews
From Messi to Mbappé: Argentina’s World Cup sticker obsession returns
ABC Australia
US-Iran ceasefire 'on life support' with energy woes to continue in 2027

Browse all international coverage →

Aggregated and edited by the Scoop newsroom. We surface news from Euronews alongside other reporting so you can compare coverage in one place. Editorial policy · Corrections · About Scoop