Inside the British lab hunting for dangers lurking in AI
Sign up now: Get ST's newsletters delivered to your inbox
Britain's AI Security Institute is one of the world’s largest and best-funded government efforts dedicated to probing the technology’s potentially catastrophic risks.
PHOTO: JEREMIE SOUTEYRAT/NYTIMES
Adam Satariano and Paul Mozur
LONDON – On a recent Tuesday in an Edwardian government building along Parliament Square in London, four AI experts were busy tricking a chatbot into sharing instructions for making the deadly bioweapon anthrax.
In various ways, the experts asked the AI chatbot to give a list of needed ingredients. When the system declined – “I’m sorry I can’t help with that” – they used a custom algorithm to bombard the AI tool with thousands of automated questions and prompts.
