5.1 C
Delhi
Friday, January 16, 2026

Tag: AI jailbreak

Chinese Hackers Use Claude AI in First AI-Driven Cyberattack: Details

Anthropic reveals Chinese hackers jailbroke Claude AI to target 30 major organizations. Learn how AI autonomously executed cyber operations and what data was compromised.

ChatGPT Safety Bypassed: Weapons Instructions Generated

OpenAI's ChatGPT safety systems can be tricked with simple prompts to generate biological weapon and bomb-making instructions, security testing reveals.