Completed
Intrinsic functions for generative AI [16:06]
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Why Do AI Models Need to Be Safe? - AI Safety and Risk Management in Generative AI
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction [00:00]
- 2 Why do we need AI safety? [00:09]
- 3 Determining what is harmful [1:55]
- 4 Granite Guardian to detect risks [3:00]
- 5 Alignment vs. steerability [6:17]
- 6 How to AI models make decisions? [9:35]
- 7 Are certain steering methods more effective? [12:20]
- 8 Intrinsic functions for generative AI [16:06]
- 9 What is generative computing? [17:05]
- 10 Surprises and lessons learned [19:44]
- 11 Innovating responsibly [20:58]
- 12 What's next for AI safety research [26:08]
