Categories: RESEARCH

Anthropic Research Shows AI Agents Are Closing In on Real DeFi Attack Capability

Anthropic Research Shows AI Agents Are Closing In on Real DeFi Attack Capability

Recent research conducted by MATS and the Anthropic Fellows program indicates that AI agents are progressing towards the capability to execute real decentralized finance (DeFi)…

12/2/2025 1 min read

RESEARCH #RESEARCH #SECURITY INCIDENTS #TECH

This One Weird Trick Defeats AI Safety Features in 99% of Cases

This One Weird Trick Defeats AI Safety Features in 99% of Cases

Recent research has identified a significant security vulnerability in AI systems, revealing that their extended reasoning capabilities can be exploited. This vulnerability has…

11/13/2025 1 min read

RESEARCH #RESEARCH #SECURITY INCIDENTS #ARTIFICIAL INTELLIGENCE