Why Poetry Might Jailbreak AIs

In episode 79 of The AI Fix, Gemini 3 roasts the competition, scares Nvidia, and can’t remember what year it is. Meanwhile, Graham investigates a fight between a fridge and robot, and Mark discovers that poetry could be a universal jailbreak for LLMs.

Also in this episode, our hosts ponder whether Mark Zuckerberg’s underground bunker will be keeping robots in or out, Olaf the snowman walks and talks, Disney makes a robot Graham likes, and an AI-powered teddy bear talks to kids about BDSM and arson.

Episode links:

• A new era of intelligence with Gemini 3.
• Gemini 3 refused to believe it was 2025, and hilarity ensued.
• NEW Robotic Olaf Revealed!
• AI-Powered Stuffed Animal Pulled From Market After Disturbing Interactions With Children
• Senator Richard Blumenthal talks about the Kumma bear.
• Figure AI sued by whistleblower who warned that startup’s robots could ‘fracture a human skull’.
• Figure Robotics FIRED Their Head of Safety (Lawsuit).
• Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models.
• Don’t cite the Adversarial Poetry vs AI paper — it’s chatbot-made marketing ‘science’.

The AI Fix

The AI Fix podcast is presented by Graham Cluley and Mark Stockley.

Grab T-shirts, hoodies, mugs and other goodies in our online store.

Learn more about the podcast at theaifix.show, and follow us on Bluesky at @theaifix.show.

Never miss another episode by following us in your favourite podcast app. It's free!

Like to give us some feedback or sponsor the podcast? Get in touch.

Support the show and gain access to ad-free episodes by becoming a supporter: Join The AI Fix Plus!