Tech

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

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.

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. 

Shares:

Related Posts

Leave a Reply

Your email address will not be published. Required fields are marked *