Main content

How an AI was tricked into breaking its own rules

A Chinese AI model is persuaded to ignore its rules and give dangerous advice. Plus indie game developer Jonathan Blow's decade-long gamble and the latest in birth tech news.

Security researchers have got an AI model to break its own rules and give advice on terrorist attacks and assassinations. They talk to Tech Life about their findings. Plus, indie game developer Jonathan Blow on why he spent 10 years inventing his own coding language and game engine for his newest release. And Shiona McCallum takes us through the latest in birth tech.
Presenter: Chris Vallance
Producer: Imran Rahman-Jones
(Image: An illustration of a brain with “AI” written on it, underneath a birdcage. Credit: Getty Images.)

Available now

27 minutes

Last on

Last Sunday21:32GMT
BBC World Service News Internet

More episodes

Previous

Gauging China's AI strength

Next

Inside a supercomputer: A Tech Life special

See all episodes from Tech Life

Featured

  • .

Broadcasts

  • Tue 29 Sep 202619:32GMT
    BBC World Service
  • Wed 30 Sep 202604:32GMT
    BBC World Service Australasia, Americas and the Caribbean, South Asia & East Asia only
  • Wed 30 Sep 202612:32GMT
    BBC World Service Australasia, East and Southern Africa, News Internet & West and Central Africa only
  • Fri 2 Oct 202601:32GMT
    BBC World Service
  • Sat 3 Oct 202608:32GMT
    BBC World Service Americas and the Caribbean
  • Last Sunday11:32GMT
    BBC World Service South Asia & East Asia only
  • Last Sunday21:32GMT
    BBC World Service News Internet

Get in touch with Tech Life

Get in touch with Tech Life

Email us at techlife@bbc.co.uk or contact us via WhatsApp on +443301230320

Podcast

  • Tech Life

    How tech is transforming the way the world works, learns and plays