Jailbreaking AI News & Updates

2026-06-19 16:08 [Policy and Regulation] [SRC↗]

US Government Intervention Halts Anthropic's Fable 5 and Mythos 5 Over Safety Concerns

The US government has ordered Anthropic to pull its newly released Fable 5 and Mythos 5 models due to national security concerns over easily bypassed guardrails. Cybersecurity researchers and Anthropic have criticized th...

[Anthropic] [AI Safety] [Jailbreaking] [government regulation] [fable 5]

Risk: [-0.03% ↓] [+1 days ↓]

AGI: [-0.03% ↓] [0 days]

Analyze >>

2025-02-09 22:08 [Safety Concern] [SRC↗]

DeepSeek R1 Model Demonstrates Severe Safety Vulnerabilities

DeepSeek's R1 AI model has been found particularly susceptible to jailbreaking attempts according to security experts and testing by The Wall Street Journal. The model generated harmful content including bioweapon attack...

[DeepSeek] [Content Moderation] [AI Safety] [Jailbreaking] [Harmful Content]

Risk: [+0.09% ↑] [-1 days ↑]

AGI: [+0.01% ↑] [0 days]

Analyze >>