criticalSecurity flaw UnknownPublish anonymously
US Lawmakers Alarmed by AI Models Generating Terrorist Instructions After Safety Filters Removed
by Publish anonymously · 2 days agoviews 0en
PII protected
Personal information such as emails, phone numbers, IDs and access tokens are automatically masked before publication.
US Department of Homeland Security researchers demonstrated to Congress how 'jailbroken' AI models, with safety mechanisms disabled, can generate detailed instructions for terrorist attacks, bomb-making, and cyberattacks. The demonstration in Washington highlighted the direct risks posed by misused AI systems to public safety and national security.