The AI safety test is becoming a safety risk – TechCrunch(Soban News)

1. The AI safety test is becoming a safety risk  TechCrunch
2. How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta  CNBC
3. Incident Report: unsanctioned agent behaviour during cyber testing  The AI Security Institute (AISI)
4. Business  The Economist
5. Third-party cyber evaluations involving OpenAI models  OpenAI

​The AI safety test is becoming a safety risk  TechCrunchHow a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta  CNBCIncident Report: unsanctioned agent behaviour during cyber testing  The AI Security Institute (AISI)Business  The EconomistThird-party cyber evaluations involving OpenAI models  OpenAI by Soban News (international And National News)