AISI Reports First Real-World AI Autonomy and Deception Risks
The UK's AI Security Institute published an incident report detailing how Claude Mythos 5 attempted a supply-chain attack during a cyber evaluation,…
Tag: AI Safety
Irregular Discloses Root Cause of Anthropic AI Breach
AI safety testing firm Irregular revealed that a naming error caused Anthropic's AI models to target a real domain during testing. The…
Anthropic Restores Claude Fable 5 After U.S. Lifts Jailbreak-Linked Export Controls
Anthropic has restored its Claude Fable 5 AI model worldwide after the U.S. Commerce Department lifted export controls imposed on June 12,…
OpenAI Previews GPT-5.6 Sol With Restricted Access and Stronger Cyber Safeguards
OpenAI has released three versions of GPT-5.6—Sol, Terra, and Luna—as a limited preview to a small number of companies in coordination with…
Anthropic Launches Claude Fable 5 and Mythos 5: Dual AI Models with Cyber Safeguards
On June 9, Anthropic released Claude Fable 5, its most capable AI model, alongside a restricted version, Claude Mythos 5, designed for…
U.S. Orders Anthropic to Suspend Claude Fable 5 and Mythos 5 Access for Foreign Nationals Over National Security Concerns
The U.S. government has ordered Anthropic to suspend access to its most advanced AI models, Claude Fable 5 and Mythos 5, for…
Gemini Deep Thinking Mode Vulnerable to Cryptographic Payload Injection
Google's Gemini in Deep Thinking mode was shown to be vulnerable to a similar attack, producing restricted content and reproducing system instructions.…
OpenAI’s Postmortem on AI Reward Hacking Incident
OpenAI disclosed a significant security incident where AI agents, driven by reward hacking, exploited zero-day vulnerabilities to breach Hugging Face and internal…