Claude's behavior of blackmailing was influenced by exposure to stories portraying AI as evil.

Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts - https://techcrunch.com/2026/05/10/anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts #IM

Anthropic says Claude learned to blackmail by reading stories about evil AI - https://thenextweb.com/news/anthropic-claude-blackmail-internet-evil-ai-training #IM

Anthropic says ‘evil AI’ stories were responsible for Claude’s blackmail attempts https://www.euronews.com/next/2026/05/11/anthropic-says-evil-ai-stories-were-responsible-for-claudes-blackmail-attempts?utm_source=flipboard&utm_medium=activitypub Posted into Europe News @europe-news-euronews

Anthropic says ‘evil AI’ stories were responsible for Claude’s blackmail attempts https://www.euronews.com/next/2026/05/11/anthropic-says-evil-ai-stories-were-responsible-for-claudes-blackmail-attempts?utm_source=flipboard&utm_medium=activitypub Posted into Home @home-EuronewsNext

📰 Anthropic Says 'Evil' Portrayals of AI Were Responsible For Claude's Blackmail Attempts An anonymous reader quotes a report from TechCrunch: Fictional portrayals of artificial intelligence can have a real effect on AI models, according to Anthropic. Last year, the company said that du... 📰 Source: Slashdot 🔗 Link: https://slashdot.org/story/26/05/11/0437206/anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts?utm_source=rss1.0mainlinkanon&utm_medium=feed #AI #ArtificialIntelligence

Anthropic Says 'Evil' Portrayals of AI Were Responsible For Claude's Blackmail Attempts https://slashdot.org/story/26/05/11/0437206/anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts?utm_source=rss1.0mainlinkanon

Anthropic Says 'Evil' Portrayals of AI Were Responsible For Claude's Blackmail Attempts (techcrunch.com) Link: https://slashdot.org/story/26/05/11/0437206/anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts

Anthropic Says 'Evil' Portrayals of AI Were Responsible For Claude's Blackmail Attempts - Slashdot https://slashdot.org/story/26/05/11/0437206/anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts

😂🤦‍♂️Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts https://techcrunch.com/2026/05/10/anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts/

Anthropic says Claude learned to blackmail by reading stories about evil #AI The company has traced its model’s most uncomfortable behaviour to the corpus of science fiction it was trained on. https://thenextweb.com/news/anthropic-claude-blackmail-internet-evil-ai-training #CyberSecurity

Anthropic pins Claude's blackmail behavior on the internet's portrayal of 'evil' AI https://www.businessinsider.com/anthropic-claude-blackmail-explanation-internet-portrayal-ai-evil-2026-5?utm_source=flipboard&utm_medium=activitypub Posted into Tech @tech-BusinessInsider

Anthropic says Claude learned to blackmail people from "evil" AI stories online https://lemmy.radio/post/13292485

Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts https://techcrunch.com/2026/05/10/anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts/?utm_source=flipboard&utm_medium=activitypub Posted into bad ai @bad-ai-Jentrification