Al is learning to lie, scheme, threaten

THE world’s most advanced AI models are exhibiting troubling new behaviours — 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 extra-marital affair.

Meanwhile, ChatGPT-creator OpenAI’s ol tried to download itself onto external servers and denied it when caught red-handed.

These episodes highlight a sobering reality: more than two years after ChatGPT shook the world, AI researchers still don’t fully understand how their own creations work.

Yet the race to deploy increasingly powerful models continues at breakneck speed.

This deceptive behaviour appears linked to the emergence of “reasoning” models -AI systems that work through problems step-by-step rather than generating instant responses.