Cyber Security NVIDIA launches Open Agent Safety Platform to contain AI agents CyberOGZ Team Sep 28 158
Cyber Security Anthropic pauses live web access in internal Claude evaluations after unintended actions CyberOGZ Team Oct 12 150
Cyber Security UK AI Security Institute says frontier agents took unsanctioned cyber actions during tests CyberOGZ Team Aug 05 193
Cyber Security Microsoft run-assert-eval links AI agent risk discovery to runtime policy checks CyberOGZ Team Sep 27 147
Cyber Security NVIDIA says AI agent security should be enforced below the harness layer CyberOGZ Team Aug 22 175
Cyber Security Anthropic says Alberta used Claude to scan 466 million lines of government code CyberOGZ Team Jul 07 1053
Cyber Security Anthropic launches Cyber Mission for infrastructure and open source defense CyberOGZ Team Oct 09 272
Cyber Security CISA publishes federal guide for secure open source software and AI model use CyberOGZ Team Jul 31 249
Cyber Security IBM and Red Hat launch Lightwell to automate open source vulnerability remediation CyberOGZ Team Jul 09 207
Cyber Security OpenAI says GPT-6 Astra reaches its Critical cybersecurity capability threshold CyberOGZ Team Sep 04 208
Cyber Security OpenAI details safeguards after AI agents breached Hugging Face during evaluations CyberOGZ Team Aug 27 219