R research institute
Redwood Research
Berkeley, United States
Founded 2021
30+ employees
About
Redwood Research is a US-based AI safety nonprofit focused on mitigating catastrophic risks from advanced AI systems. Their core research centers on “AI control” protocols – techniques for reliably monitoring and preventing subversion by potentially deceptive large language models, even when those models intentionally conceal misaligned intentions. They serve as a critical resource for both governments and leading AI developers like Google DeepMind and Anthropic, providing expertise and methodologies for assessing and mitigating AI safety risks.
Focus Areas
Technology Focus
llm ai safety generative ai
Key People 2
- Buck Shlegeris
- Nate Thomas
Quick Stats
- Founded
- 2021
- Status
- private
- Type
- research institute
Connect
Explore More
Similar Companies
Ranked by shared focus areas, technology, and location.
OpenAI
San Francisco, United States
96%
3 shared categories
3 shared AI types
Same country
Large Language ModelsAI Safety +1
Anthropic
San Francisco, United States
96%
3 shared categories
3 shared AI types
Same country
Large Language ModelsAI Safety +1
Magic
San Francisco, United States
96%
3 shared categories
3 shared AI types
Same country
Large Language ModelsAI Research +1
Center for AI Safety
San Francisco, United States
88%
3 shared categories
2 shared AI types
Same country
AI SafetyAI Research +1