Hypothesis

1 Matching Annotations

May 2025
www.niemanlab.org www.niemanlab.org

Anthropic’s new AI model didn’t just “blackmail” researchers in tests — it tried to leak information to news outlets

1
1. stopresetgo 30 May 2025
  
  in Public
  
  for - progress trap - AI - Anthropic Claude 4 - blackmail - from - youtube - Kyle Kilinski Show - AI is completely out of control - https://hyp.is/GhDOzj0nEfCvHZdiUaw4gQ/www.youtube.com/watch?v=4j1gjSoRt8Q
  
  progress trap - AI - Anthropic Claude 4 - blackmail from - youtube - Kyle Kilinski Show - AI is completely out of control
Visit annotations in context

Tags

from - youtube - Kyle Kilinski Show - AI is completely out of control

progress trap - AI - Anthropic Claude 4 - blackmail

Annotators

stopresetgo

URL

niemanlab.org/2025/05/anthropics-new-ai-model-didnt-just-blackmail-researchers-in-tests-it-tried-to-leak-information-to-news-outlets/