Writing backwards can trick an AI into providing a bomb recipe

State-of-the-art generative AI models like ChatGPT can be tricked into giving instructions on how to make a bomb by simply writing the request in reverse, warn researchers.

Large language models (LLMs) like ChatGPT are trained on vast swathes of data from the internet and can create a range of outputs – some of which their makers would prefer didn’t spill out again. Unshackled, they are equally likely to be able to provide a decent cake recipe as know how to make explosives from household chemicals.