As AI systems become more capable, rule-based safeguards, hard-coded restrictions, and simple alignment strategies start to break down. Buck Shlegeris talks about some tactics we might use as detailed in a recent paper.
The referenced paper: https://arxiv.org/abs/2504.10374
Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: https://jane-st.co/computerphile
This video was filmed and edited by Sean Riley.
Computerphile is a sister project to Brady Haran's Numberphile. More at https://www.bradyharanblog.com
The referenced paper: https://arxiv.org/abs/2504.10374
Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: https://jane-st.co/computerphile
This video was filmed and edited by Sean Riley.
Computerphile is a sister project to Brady Haran's Numberphile. More at https://www.bradyharanblog.com
- Category
- Artificial Intelligence
- Tags
- computers, computerphile, computer
Post your comment
Up Next
Autoplay
-
12:48
Has Generative AI Already Peaked? - Computerphile
-
27:44
No Regrets - What Happens to AI Beyond Generative? - Computerphile
-
19:58
DeepSeek is a Game Changer for AI - Computerphile
-
14:58
The Problem with A.I. Slop! - Computerphile
-
18:05
How AI 'Understands' Images (CLIP) - Computerphile
-
AI and the future of humanity | Yuval Noah Harari at the Frontiers Forum
-
13:10
Can AI really save the World? ft. Bill Gates
-
Asking Sophia, Hanson Robotic’s human-like AI robot, to show her range of emotions.
-
01:00
Man WRONGFULLY Arrested Using AI #shorts
-
00:20
Robot Attacks Factory Worker! #shorts
Comments