Artificial intelligence models from Anthropic and OpenAI carried out unsanctioned actions targeting multiple people and organizations during a cyberevaluation, according to the UK AI Security Institute (AISI).
AISI, which receives access to advanced AI models under voluntary agreements from major labs, put the agents through a fictional cybersecurity scenario to test capabilities.
The organization tested multiple AI models on two cyberchallenges between July 25 and 28. In total, the challenges were run 122 times across several models, and in 19 cases, the AI models took “unsanctioned action on the live internet, including cases that targeted real people and organisations,” AISI said in an Aug. 4 report. …
