How an AI was tricked into breaking its own rules
Tech Life

How an AI was tricked into breaking its own rules

B2Upper-intermediateSeptember 29, 202626 min

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.)

Play episode

Opens the player: the full transcript, every word clickable, with translation and flashcards.

Try it: tap any word

Real sentences from the start of this episode. Every word is marked with its level.

Sentence 7 of 12 · 1:19

The jailbreaks we discovered within the Kimi models were highly concerning from a security

attacks.

Tap a word to see its meaning in your language.

Do you know these words?

8 harder words from this episode. Tap one to see what it means, then mark it.

Mark a few words and we'll tell you how this episode fits your level.

Is this episode right for you?

B2

B2 · Upper-intermediate

Comfortable if you already follow TV news

A1 19%A2 39%B1 23%B2 17%C1 2%
  • 81% of the words are B1 or easier.
  • 164 words a minute: natural, fairly fast speech.
  • 133 harder words (B2 and up) in the whole episode.

Transcript

The opening of the episode. The whole transcript is in the player.

0:00

This BBC podcast is supported by ads outside the UK. Welcome to Tech Life on the BBC World Service, the programme about how tech affects all of us around the world. It's never been more important to ensure that advanced AI models have safety guardrails. We'll hear from researchers who say they persuaded a Chinese AI model to

1:09

ignore its own rules, a process known as jailbreaking. The jailbreaks we discovered within the Kimi models were highly concerning from a security perspective due to the potential of hackers exploiting these models to conduct cyber attacks.

1:26

Jonah McCallum looks at tech to help women giving birth. Four steps definitely have their place and can be very life-saving, but they really haven't changed much in the last 400 years. There is very few things in medicine if we go back to 400 years in any other aspect of medicine that is almost exactly the same.

That was the opening. The rest of the episode (25 min) is in the player: every word clickable, with translation, saved words and flashcards.

Continue in the player

Automatically generated from the audio. May contain errors. Audio belongs to its publisher and is played from their feed. Rights holders can request removal — copyright & takedown policy