Sign In

Cooper Raterink

Exploring in the Edtech X Generative AI space

Cooper Raterink is a professional engaged in the field of artificial intelligence (AI) safety and ethics. He has a background in computer science education, having served as a Computer Science Instructor at Code.X from June 2019 to July 2022, where he taught tech entrepreneurship to high school students.1

Raterink's research interests are focused on AI fairness, bias, safety, and ethics, and he has contributed to significant projects in these areas. Notably, he is involved with the WMDP Benchmark, which aims to measure and reduce the malicious use of AI systems. This benchmark is designed to evaluate the hazardous knowledge that AI models may possess and to develop methods for "unlearning" this knowledge while maintaining the models' general capabilities.24 His work emphasizes the importance of creating safer AI systems by addressing potential risks associated with their deployment.

Additionally, Raterink has been active in presenting his research findings and has a personal website that outlines his work and contributions.3 His professional profile on LinkedIn reflects his academic and teaching background, showcasing his commitment to educating others about technology and its implications.1

Highlights

Jan 3 · dl.acm.org
The WMDP benchmark: measuring and reducing malicious use with ...
Jan 27 · arxiv.org
[PDF] Low-Resource Languages Jailbreak GPT-4 - arXiv
Dec 28 · cooperraterink.com
Example Talk - Cooper Raterink

Related Questions

What projects has Cooper Raterink worked on at Stealth?
How did Cooper Raterink transition from teaching to a career in tech?
What are some notable achievements of Cooper Raterink in the field of AI safety?
What is the role of Cooper Raterink at Stealth?
How does Cooper Raterink contribute to the development of AI safety measures?
Cooper Raterink
Cooper Raterink, photo 1
Cooper Raterink, photo 2
Add to my network

Location

New York, New York, United States