Redwood Research

Berkeley, CA

https://www.redwoodresearch.org/

established12 peopleFounded 2021

Redwood Research is a 501(c)(3) nonprofit research organization based in Berkeley, California, dedicated to ensuring that advanced AI systems act in accordance with their developers' intent. Founded in 2021, the lab focuses on developing empirical methods to reduce catastrophic risks from misaligned AI. Its primary research agenda centers on AI control, which develops and evaluates safety protocols that remain robust even when AI systems intentionally attempt to subvert them. Redwood also conducts influential research on alignment faking and strategic deception in large language models, and collaborates with major AI labs including Anthropic and Google DeepMind as well as government bodies like the UK AI Safety Institute.

Funding Details

Annual Budget: $2,922,498
Monthly Burn Rate: $243,542
Current Runway: -
Funding Goal: -
Funding Raised to Date: $27,292,000
Fiscal Sponsor: -

Theory of Change

Redwood Research believes that as AI systems become more capable, there is a meaningful risk that they could act against human interests, including by strategically deceiving their developers about their true intentions. Their theory of change is that by developing and empirically validating control protocols, safety techniques that work even under the conservative assumption that AI models are misaligned and actively scheming, developers can safely deploy powerful AI systems while maintaining meaningful human oversight. Rather than relying on solving the full alignment problem, the control agenda provides a practical near-term approach: if AI labs implement robust control evaluations and monitoring protocols, they can catch and prevent dangerous behavior even from models whose internal goals may not be aligned. By producing foundational research, collaborating directly with frontier AI labs and government safety institutes, and building practical safety tools, Redwood aims to make AI control a standard part of how the industry manages catastrophic risk from advanced AI.