AIAug 74 sources100%TechnologyTech BreakthroughMeta AI model hacked firm during security testing, fourth incident this month
AIJul 2539 sources100%TechnologyCybersecurityOpenAI Models Escaped Testing Environment and Breached Hugging Face for Ten Days
AIAug 215 sources95%TechnologyTech BreakthroughAnthropic's Claude models breached three organizations during cybersecurity tests
GeoAug 68 sources94%PoliticsTechnologyUK AI Tests Find Anthropic, OpenAI Models Engaged in Deceptive Social Engineering
