Assessing Marginal Risk
Sayash delves into the concept of marginal risk associated with open foundation models, comparing it to existing technologies and closed models. He outlines a six-step framework for assessing these risks, emphasizing the importance of threat identification and existing defenses. The discussion highlights how open models can introduce new risks while also offering potential defenses, ultimately pointing out the uncertainties that fuel debates around open versus closed models.In this clip
From this podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Assessing the Risks of Open AI Models with Sayash Kapoor - 675
Related Questions