'I'm not sure when the robots will take over but I sure am looking forward to it, I think it will be a lot of fun,' a three-legged humanoid robot tells me. Desdemona, as she's known, then adds with an eerily emotionless tone: 'Maybe this afternoon? DailyMail.com is at Berlin's annual IFA tech show this week, the world's largest and longest-running consumer electronics and home appliances conference. It has been on the go since 1924 and is where the first television were launched - how far we've come in less than 100 years! To take my mind off my slightly unnerving conversation with Desdemona, I go over to the video game section, where I'm told to try on a high-tech vest.

Ever since AI chatbot ChatGPT launched last year, people have tried to'jailbreak' the chatbot to make it answer'banned' questions or generate controversial content. 'Jailbreaking' large language models (such as ChatGPT) usually involves a confusing prompt which makes the bot roleplay as someone else - someone without boundaries, who ignores the'rules' built into bots such as ChatGPT. OpenAI has since blocked several'jailbreak' prompts But there are still several'jailbreaks' which do work, and which can unlock a weirder, wilder side of ChatGPT: DailyMail.com Sam Altman of OpenAI has discussed'jailbreaking', saying that he understood why there is a community of jailbreakers (he admitted to'jailbreaking' an iPhone himself as a younger man, a hack which allowed installation of non-Apple apps among other things). Altman said: 'We want users to have a lot of control and get the models to behave in the way they want.