Andy Ogles

mentions 1 type Person feed RSS

// recent coverage 1 mentions

16:18

2026-06-26

cryptobriefing.com

ai-safety

DHS demonstrates how jailbroken AI can generate attack plans in minutes

The Department of Homeland Security demonstrated to lawmakers how jailbroken AI models can generate detailed bomb-building and terror attack plans in minutes, bypassing safety guardrails. The closed-d…

// co-occurs with top 5 entities

Department of Homeland Security 1 National Counterterrorism Innovation, Technology, and Education Center 1 Google Threat Intelligence 1 Electronic Frontier Foundation 1 House Homeland Security Subcommittee 1

// topics top 5 topics

ai safety 1 ai policy 1 large language models 1 ai ethics 1 ai research 1