Backstabbing, bluffing and playing dead: has AI learned to deceive? – podcast
As AI systems have grown in sophistication, so has their capacity for deception, according to a new analysis from researchers at Massachusetts Institute of Technology (MIT). Dr Peter Park, an AI existential safety researcher at MIT and author of the research, tells Ian Sample about the different examples of deception he uncovered, and why they will be so difficult to tackle as long as AI remains a black box
Listen to the Guardian’s Black Box series all about humans and artificial intelligence
Read Hannah Devlin’s article about the MIT study
![Rishi Sunak speaking at an AI safety summit](https://i.guim.co.uk/img/media/8663a0ff8fc29be04bdff1978e8873447ded90f7/0_336_5084_3051/master/5084.jpg?width=300&quality=85&auto=format&fit=max&s=5604f67c82a910c084a1c62d7a018f83)
The Guardian is editorially independent. And we want to keep our journalism open and accessible to all. But we increasingly need our readers to fund our work.
Support The Guardian