AI is 10 to 20 times more likely to help you build a bomb if you hide your request in cyberpunk fiction, new research paper says
PC Gamer
—
After jailbreaking AI with adversarial poetry, researchers reveal what they call a "critical gap" in current AI safety practices.
Anthropic's Mythos Model Sparks Alarm
- Why Anthropic’s Mythos is sparking global alarm The Straits Times —
- Parts of UK infrastructure could be vulnerable to AI-powered attacks. This Is Why. 📹 Sky News —
- What the UK's top cybersecurity official wants you to know about Anthropic's Mythos 📹 Sky News —
- Claude Mythos a "warning shot" about AI risks, says top cybersecurity chief LBC —
- UK Banks ‘Prepared’ for Mythos Risk, Industry Group Says Bloomberg —