Carnegie Mellon researchers have shown that large language models (LLMs) can autonomously plan and execute cyberattacks in enterprise environments, marking a significant advancement in the understanding of LLM capabilities in cybersecurity. Their study, which replicated the 2017 Equifax breach scenario, highlights both the risks of LLM misuse and potential benefits for enhancing security testing in organizations. The team is now exploring how LLM-based agents can be used for autonomous defense against cyber threats.