Introducing EVMbench
OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities.
Updated 1 min ago · 2 articles from OpenAI Blog
OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities.
OpenAI banned accounts potentially associated with publicly reported DPRK-affiliated threat actors using AI to research intrusion tooling, phishing, malware,...