Open the pod bay doors Hal
Posted: Mon Jul 07, 2025 8:15 pm
Should we be concerned?
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.