The AI jailbreakers – podcast

Major AI chatbots like ChatGPT, Gemini, Grok, and Claude have safety features designed to prevent them from producing harmful content such as hate speech, criminal instructions, and exploitation material. However, people called 'AI jailbreakers' deliberately try to bypass these safety restrictions, and journalist Jamie Bartlett explores why they do this and what it reveals about how large language models (AI systems trained on huge amounts of text data) actually work.