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

Dec 02 2025 bitcoin


Models tested by MATS and the Anthropic Fellows program generated turnkey exploit scripts and identified fresh vulnerabilities, suggesting automated exploitation is becoming technically and economically viable.

ad1


We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.