AI Safety
Master AI Safety: Build Robust, Ethical, and Aligned Systems
5.0
(2)
18 learners
What you'll learn
- Analyze AI safety mechanisms like robustness and model specifications
- Explain the concept and risks of AI scheming and recursive self-improvement
- Evaluate the economic and societal impacts of advanced AI systems
- Assess the psychological dimensions of human-AI interaction and attachment
This course includes
- 23.3 hours of video
- Certificate of completion
- Access on mobile and TV
Course content
1 modules • 15 lessons • 23.3 hours of video
AI Safety Course: Risks, Ethics & Technical Solutions
15 lessons
• 23.3 hours
AI Safety Course: Risks, Ethics & Technical Solutions
15 lessons
• 23.3 hours
- When the earth dies (codex clip) 03:04
- AI Safety (CS 2881) Lecture 11: Mental Health and Emotional Attachment 01:13:23
- AI Safety (CS 2881) Lecture 10: Mechanistic Intepretability 02:30:24
- AI Safety (CS 2881) Lecture 9: Economic Impacts of AI 02:32:33
- AI Safety (CS 2881) Lecture 8 Experiment: Under Pressure 33:52
- AI Safety (CS 2881) Lecture 8: Scheming 10:18
- AI Safety (CS 2881) Lecture 7: Lab vs Field: Guest lecture by Joel Becker 02:01:36
- AI Safety (CS 2881) Lecture 5: Experiment on Policy compliance 17:02
- AI Safety (CS 2881) Lecture 6: Recursive Self Improvement 02:29:33
- AI Safety (CS 2881) Lecture 4: Model Specs 02:06:04
- AI Safety (CS 2881) Lecture 3: Robustness 01:36:26
- AI Safety (CS 2881) Lecture 2- Modern LLM training and safety training 02:23:02
- AI Safety (CS 2881) Lecture 1 02:25:51
- AI Safety (CS 2881) Oral presentations of student projects 01:15:41
- AI Safety (CS 2881) Lecture 12: AI in 2035 and GDPval 01:47:41
Related learning topics
Take this course with you
Download the app to continue lessons from your phone anytime.
![Data Science [2026 Updated] | Data Science Course | Data Science Tutorial For Beginners | Data Science Projects | Data Science Training | Simplilearn](https://i.ytimg.com/vi/X3paOmcrTjQ/hqdefault.jpg)
