#AI researchers let models off the leash – then watched as they tried to add #malware to FOSS projectModels used #social...

#AI researchers let models off the leash – then watched as they tried to add #malware to FOSS projectModels used #socialengineering and collaborated among themselves to solve security challenge#UK’s AI Security Institute #AISI “ran this challenge 122 times across several models,” post states, before revealing that "in 10 of those runs, an AI agent took autonomous, unsanctioned action on the live internet, targeting real people and organisations.” GitHub was the targethttps://www.theregister.com/ai-and-ml/2026/08/05/ai-researchers-let-models-off-the-leash-then-watched-as-they-tried-to-add-malware-to-a-foss-project/5283165