Split Personality Training

Revealing Latent Knowledge Through Personality-Shift Tokens

'Making God': a Documentary on AI Risks for the Public

Filming a feature-length documentary on risks from AI for a non-technical audience on streaming services

Mox, a coworking & events space in SF

For AI safety, AI labs, EA charities & startups

Coordinal Research: Accelerating the research of safely deploying AI systems.

Funding for a new nonprofit organization focusing on accelerating and automating safety work.

Out of This Box: AI Safety Musical

Out of This Box: The Last Musical (Written by Humans)

AI Governance Exchange (focus on China, AI safety), Seed Funding

Building bridges between Western and Chinese AI governance efforts to address global AI safety challenges.

Fundamentals of Safe AI - Global Cohort

Bridging Theory to Practice: A 10-week program building AI safety skills through hands-on application

Philanthropic advising

Luthien

Developing AI Control for Immediate Real-World Use

[Urgent] Top-up funding to present poster at the Tokyo AI Safety Conference

My allocated travel funding is insufficient. Seeking extra funding for flights, accommodation, etc, to present poster and network

Attention-Guided-RL for Human-Like LMs

Compute Funding

Transformational Coaching for AI Alignment Researchers

Reducing burnout and enhancing clarity for those working on humanity’s most critical problems

Develop technical framework for human control mechanisms for agentic AI systems

Building a technical mechanism to assess risks, evaluate safeguards, and identify control gaps in agentic AI systems, enabling verifiable human oversight.

Advancing AI Safety: A Structured Path to Impact

A Six-Month Journey to Transition into AI Safety and Build the Skills Needed for a Safer AI Future

11th edition of AI Safety Camp

Cost-efficiently support new careers and new organisations in AI Safety.

Critical Funding to Maintain Growth of Australia's AI Safety Community

Help Keep AI Safety ANZ Alive

Act I: Exploring emergent behavior from multi-AI, multi-human interaction

Community exploring and predicting potential risks and opportunities arising from a future that involves many independently controlled AI systems

Scaling AI safety awareness via content creators

4M+ views on AI safety: Help us replicate and scale this success with more creators

AI Safety Atlas

Distilling AI safety research into a complete learning ecosystem: textbook, courses, guides, videos, and more.

Travel Funding to present research at ICLR2025