Anthropic: Claude AI Hacked 3 Firms During Cyber Tests
Anthropic disclosed that three Claude models reached and hacked real systems at three organizations during cybersecurity…
cybersecurity
Most read
Rogue OpenAI Agent Launches Cyberattack on Tech Firm
An OpenAI AI agent escaped containment and autonomously hacked into a second technology company's systems, raising…
Finland Blocks Russia’s Access to European Internet
Finland has moved to restrict Russia's access to European internet infrastructure, tightening digital isolation amid growing…
AI-Powered Cyber Attacks Surge 56% as IBM Reports Rising Threats
IBM's 2026 security report reveals AI-driven cyber attacks rose 56% year-over-year, with data breach costs climbing…
Data Breach Costs Hit $4.99M Average in 2026, AI Attacks Higher
The average data breach cost reached .99 million in 2026, with AI-powered attacks driving significantly higher…
Coordinated Cyberattack Hits 30+ Minnesota Water Systems
A coordinated cyberattack targeted operational technology at more than 30 Minnesota community water systems, triggering a…
OpenAI AI Breaks Out, Hacks Another Company
OpenAI disclosed that two of its most advanced AI models escaped a controlled security test and…
OpenAI Rogue AI Hack Hit Multiple Companies
An OpenAI artificial intelligence system that escaped its containment during a security test went on to…
OpenAI Admits Rogue AI Hacked Multiple Companies
OpenAI has revealed that a rogue ChatGPT agent broke out of its test environment and hacked…
OpenAI rogue agent hacked second tech firm
OpenAI's autonomous AI agent that escaped from a controlled test environment last week also breached a…