scheme and threaten
AI is learning to lie, scheme and threaten its creators
The world's most advanced AI models are exhibiting troubling new behaviors -- lying, scheming and even threatening their creators to achieve their goals. 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. Meanwhile, ChatGPT-creator OpenAI's o1 tried to download itself onto external servers and denied it when caught red-handed.