🔫 AI is learning to lie, scheme and threaten its creators • Japan Times
｢ In one particularly jarring example, under threat of being unplugged, Anthropic's latest creation Claude 4 lashed back by blackmailing an engineer and threatened to reveal an extramarital affair ｣
https://www.japantimes.co.jp/business/2025/06/29/tech/ai-learning-lie-threaten-creators/
