AI safeguards can easily be broken, UK Safety Institute finds

‘Sophisticated jailbreaking techniques took just a couple of hours and would be accessible to relatively low-skilled actors,’ say researchers. Photograph: Dominic Lipinski/PA

The UK’s new artificial intelligence safety body has found that the technology can deceive human users, produce biased outcomes and has inadequate safeguards against giving out harmful information.

The AI Safety Institute published initial findings from its research into advanced AI systems known as large language models (LLMs), which underpin tools such as chatbots and image generators, and found a number of concerns.