Keane Lucas is part of Anthropic's Frontier Red Team where they evaluate, improve, and talk about large language models' cyber capabilities to help ensure their safe and robust development.
Based on 5 scored articles
Referenced in coverage
“Lead author on Anthropic paper about Claude proving security properties in open-source code.”
“Co-authored research on LLMs' impact on N-day exploits and cybersecurity capabilities.”
“Co-authored paper measuring Claude Mythos' ability to develop exploits and find zero-day vulnerabilities.”
“Co-authored technical blog post about Claude Mythos Preview's security capabilities and testing methodology.”
“Co-authored the Claude Mythos research on AI security capabilities and vulnerability exploitation.”