Tech Life
World Service , · 16 Jun 2026 , · 26 mins A group of cybersecurity researchers found a prompt which gets past ChatGPT’s guardrails and causes it to generate some disturbing images. We unpack what this tells us about the way AI is trained, and how it could be exploited. Also on t
A group of cybersecurity researchers found a prompt which gets past ChatGPT’s guardrails and causes it to generate some disturbing images. We unpack what this tells us about the way AI is trained, and how it could be exploited.
Also on the show, after a recent episode about potholes, we were contacted by the UK’s ministry of transport. We speak to their chief scientific adviser about potholes and the future of transport.
And what is a quantum diamond magnetometer? We speak to the company which has just put one into space – in order to measure where magnetic north really is.
(Image: A phone with the white and black ChatGPT logo on it. In the background is green Matrix-style code. Credit: Getty Images)
