Nicholas Carlini – Black-hat LLMs [video]
Summary
The article refers to a YouTube video titled 'Nicholas Carlini – Black-hat LLMs [video]'. The provided data does not include content beyond YouTube navigation, but the topic suggests a security-focused discussion on how large language models could be exploited by malicious actors, and potential defense strategies. The video likely covers threats such as prompt injection, model manipulation, and data exfiltration, with implications for developers and security professionals.