The Alignment Problem: How To Tell If An LLM Is Trustworthy
The AI Daily Brief (Formerly The AI Breakdown): Artificial Intelligence News and Analysis
00:00
Enhancing AI Safety Through Real-World Testing and Evaluation Frameworks
This chapter explores a new initiative in Las Vegas aimed at enhancing AI safety through the testing of major AI models. It delves into the red-teaming AI village event at DEF CON 31 and introduces a research study on the trustworthiness of large language models, focusing on seven key dimensions of AI alignment.
Transcript
Play full episode
