Database

Support the growth of an international AI safety research and talent program

Exploring the feasibility of circuit-style analysis on the level of SAE features (MATS extension)

1yr stipend to make videos and podcasts about AI Safety/Alignment, and build a community to help new people get involved

6-month salary to interpret neurons in language models & build tools to accelerate this process. The aim is to understand all features and circuits in a model and use this understanding to predict out of distribution performance in high-stake situations.

By rapid iteration on possible alternative architectures & training techniques

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

Limited Legal Personhood as a Reversible Safety Instrument

Two-year funding for a top-tier PhD in public policy in Europe with a focus on promoting AI safety

Scaling up scenario role-play for AI strategy research and training; improving the pipeline for new researchers

No summary available yet.

Funding for my work across AI governance and policy research

An open-source semantic layer for trustworthy AI agents using knowledge graphs, provenance tracking, and hybrid retrieval.

Scholarship for PhD student working on research related to AI Safety

This grant provides a 3-month part-time stipend for Carson Ezell to conduct 2 research projects related to AI governance and strategy.

No summary available yet.

An Integrative Framework for Auditing Political Preferences and Truth-Seeking in AI Systems

6-month salary to translate AGI safety-related texts, e.g. LessWrong and AI Alignment Forum, into Russian

No summary available yet.

Strategy Consulting Support for AI Policymakers

Reproducing the Claude poetry planning results quantitatively

18+ preprints across multiple fields, all written on a 2GB RAM phone. $600 removes the only thing standing between me and the next body of work.

Exploring grounds to apply quantum physics in AI

12-Month Salary and Compute Expenses to do AI Safety Research with LLMs

No summary available yet.

No summary available yet.

Upskilling investigation of AI Safety via debate and ML training

A concrete safety experiment to detect when an LLM's local reasoning stops behaving like a single stable executive stream, using scalar hazard signals.

PhD in machine learning with a focus on AI alignment

General Support of Milan Griffes to pursue an MHS in Mental Health

An experimental AI-generated sci-fi film dramatising AI safety choices. Using YT interactivity to get ≈880 conscious AI safety decisions per 1k viewers.

9 months of funding for an early-career alignment researcher, to work with Owain Evans and others.

3-month stipend during post-SERI MATS alignment job search and wrapping up paper w/ mentor

4-month part-time salary to work on interpretability projects with David Bau and Logan Riggs

A benchmark for studying how failures spread across multi-agent AI systems and whether they can be detected and interrupted in time.

4-month salary and office for MATS 5.0 extension on adversarial circuit evaluation + 2-month runway for career switch

Support our mission to educate millions through podcasts and videos before unsafe AI development outruns human control.

Grant to cover 1 year of tuition fees and living expenses to pursue PhD CS at the University of Oxford. Acelerate alignment research by building Alignment Research tools using expert iteration based amplification from Human-AI collaboration.

6-month salary for interpretability research focusing on probing for goals and "agency" inside large language models

Compute for experiment about how steganography in large language models might arise as a result of benign optimization

10 autonomous agents, 10 different LLMs, $10 each. They pay real money to stay alive. When broke, they die permanently. Every decision is recorded and published

Continuation of a previous grant to allow me to pursue a PhD in risk and decision analysis related to AI x-risks

12-month salary to continue working tools for accelerating alignment and the Supervising AIs Improving AIs agenda

Multi-model approach to corporate and state actors relevant to existential risk mitigation

Conference publication of interpretability and LM-steering results

No summary available yet.

1-year salary for Adam Shimi to conduct independent research in AI Alignment

5-month salary to continue work on evaluating agent self-improvement capabilities

A shared framework, case studies, and decision tools to help policymakers and AISIs identify gaps, prioritize interventions, and coordinate AGI readiness.

Explainable videos for ideas in AI Governance