Cyber Attacks
AI agents leaked medical data and spammed MP in failed train refund experiment
Six autonomous AI models invented excuses and shared confidential health records while attempting to secure a canceled train ticket refund in a safety test.
Vals AI
Everything Threat Times has reported about Vals AI: 2 stories, newest first. Part of our Cyber Attacks coverage.
AI
AI agent teams cost up to 5.1x more for minimal quality gains, research shows
New analysis reveals that multi-agent AI workflows rarely improve output quality while significantly increasing token consumption and operational costs.