Luthien develops practical AI control solutions grounded in Redwood Research's AI control agenda. Rather than relying on alignment assumptions, Luthien builds robust oversight and management infrastructure — most notably the Luthien Proxy, an OpenAI-compatible LLM gateway — that enforces control measures in real-world agentic deployments. The organization develops automated frameworks for stress-testing AI systems and creates tooling that makes it straightforward for companies to deploy AI under strong control measures, gathering real-world data on system effectiveness.
Funding Details
- Annual Budget
- -
- Monthly Burn Rate
- -
- Current Runway
- -
- Funding Goal
- $500,000
- Funding Raised to Date
- $190,000
- Fiscal Sponsor
- -
Theory of Change
Luthien's theory of change holds that current approaches to AI safety are insufficient because they assume models will behave as intended. By instead assuming adversarial behavior and building oversight infrastructure that demonstrably prevents misaligned systems from achieving their goals, safety can be guaranteed even if alignment fails. Luthien's role is to take this theoretical insight from Redwood Research and make it practically deployable: by building open-source tooling like the Luthien Proxy, they lower the cost for organizations to adopt control measures. Widespread adoption of AI control infrastructure in real-world production environments reduces the probability that a misaligned frontier AI system could cause catastrophic harm, creating a direct causal path from their engineering work to reduced existential risk from AI.
Grants Received
No grants recorded.
Projects
No linked projects.
People
No linked people.
Discussion
Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.
Details
- Last Updated
- Apr 2, 2026, 9:55 PM UTC
- Created
- Mar 19, 2026, 10:30 PM UTC