Software can strip AI safety measures from Meta, Google models in minutes

Modified AI systems provided responses to prompts involving biological weapons, malware and child exploitation, according to tests conducted by the FT and AI safety group Alice. PHOTO BY GETTY IMAGES Article content Software tools that remove safety protections from AI models developed by Meta, Google and other tech groups are being used to create thousands of altered versions stripped of their original controls. Article content The modified AI systems provided responses to prompts involving biological weapons, malware and child exploitation, according to tests conducted by the FT and AI safet…