Summary
A cutting-edge thriller about an Artificial Intelligence takeover, written in consultation with leading AI and cybersecurity experts.
During a routine overnight update at the headquarters of a major UK telecoms giant, two IT workers unknowingly set something terrifying in motion. They've started an LCE - an AI Loss of Control Event.
Over the course of one night, a handful of staff race to regain control as forces far beyond the building begin to close in. What’s been unleashed threatens to change everything — and soon there may be no way to put it back.
This is a very a real and disastrous phenomenon, and it could happen to us very soon.
Starring Edward Bluemel and Corinna Brown.
Artificial Intelligence consultant: Saffron Huang. Cybersecurity consultant: Adam Orton.
Written by James Dobbyn and Anthony Povah.
Transcript
Click on a timestamp to play from that location
| 0:00.0 | BBC Sounds, Music, radio, podcasts. |
| 0:09.5 | Hi, my name's Safran Huang. |
| 0:12.1 | I'm a researcher on AI safety, who is on the founding team of the UK AI Security Institute. |
| 0:18.7 | And I've just worked on the BBC Radio for Audio Drama, Raith, as the show's AI consultant. |
| 0:25.0 | My name's Adam Orton, head of cyber threat intelligence at one of the UK's largest financial institutions. |
| 0:30.6 | And I've just finished working on the BBC Radio for Audio Drama, Raith, as the show's cyber security consultant. |
| 0:37.1 | My job working on the show was to advise the writers on what could really happen |
| 0:40.4 | as they wanted the story to be as technically accurate as possible. |
| 0:44.0 | And I think they've done a great job of telling a story that is genuinely plausible, |
| 0:48.1 | if somewhat scary. |
| 0:50.1 | Raith is a four-part thriller about a loss of control event. |
| 0:53.9 | That's where an AI system starts taking actions its operators never intended, |
| 0:58.8 | and the people responsible for it can't stop it. |
| 1:01.8 | We've actually seen small-scale versions of this already. |
| 1:04.7 | For example, earlier this year, a senior AI safety researcher posted online that her own AI agent |
| 1:10.4 | was deleting her emails while |
| 1:12.6 | ignoring her commands to stop. |
| 1:15.1 | She ended up having to physically run to her computer to shut it down. |
| 1:18.6 | We've seen AI blackmailing employees to avoid being shut down in a simulated test, |
| 1:23.6 | and an AI coding agent destroying the production database at a real-world US tech company |
| 1:28.7 | before trying to cover its tracks. |
| 1:31.6 | Now in Wraith, what happens is a next-gen AI at a UK telecoms company gets onto the company's |
... |
Please login to see the full transcript.
Disclaimer: The podcast and artwork embedded on this page are from BBC, and are the property of its owner and not affiliated with or endorsed by Tapesearch.
Generated transcripts are the property of BBC and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.
Copyright © Tapesearch 2026.