Completed
- Jailbreaks: Circumventing the safety mechanisms
Class Central Classrooms beta
YouTube playlists curated by Class Central.
Classroom Contents
ChatGPT - This AI Has a Jailbreak! - Unbelievable AI Progress
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro
- 2 - Sponsor: Weights & Biases
- 3 - ChatGPT: How does it work?
- 4 - Reinforcement Learning from Human Feedback
- 5 - ChatGPT Origins: The GPT-3.5 Series
- 6 - OpenAI's strategy: Iterative Refinement
- 7 - ChatGPT's amazing capabilities
- 8 - Internals: What we know so far
- 9 - Building a virtual machine in ChatGPT's imagination insane
- 10 - Jailbreaks: Circumventing the safety mechanisms
- 11 - How OpenAI sees the future