Distinguishing Intelligence from Agency in Frontier AI Systems

Empirical testing of whether AI capability scaling leads to emergent agency or shutdown resistance in frontier systems.

Compassion Bench

Open Welfare Alignment Evals for Frontier Models

Mitigating Reward Hacking Through RL Training Interventions

Safe AI Germany (SAIGE)

Germany’s talents are critical to the global effort of reducing catastrophic risks brought by artificial intelligence.

Law School for AI Governance

Support my postgraduate law studies and research in AI Governance

Agent Island: An Environment for Interagent Cooperation and Conflict

A flexible simulation environment for assessing strategic and persuasive capabilities, benchmarking, and agent development, inspired by reality TV competitions.

Seed Funding For Geodesic Research

AI Crisis Convening at India AI Impact Summit 2026

Translating in-person convening to measurable outcomes

Help a Bootstrapped AI Risk Literacy Founder Get To IASEAI 2026 in Paris

Nutrition labels transformed food safety through informed consumer choice, help me do the same for AI and make this standard :)

Ambitious AI Alignment Seminar

One Month to Study, Explain, and Try to Solve Superintelligence Alignment

12th Edition of AI Safety Camp

Real-Time Detection of Hallucinations in Large Language Models

Measuring and Visualizing Model Uncertainty During Inference

Eliminating the Effective Altruism (EA) Grant Evaluation Bottleneck with Graev

Seeking funding to secure API infrastructure and permanently eliminate the rate limits bottlenecking open-source EA grant evaluation.

Transluce: Fund Scalable Democratic Oversight of AI

Isolating CBRN Knowledge in LLMs for Safety - Phase 2 (Research)

Expanding proven isolation techniques to high-risk capability domains in Mixture of Expert models

[Retroactive] Funding for developing new "substrate-flexible risk" threat model

I self-funded research into a new threat model. It is demonstrating impact (accepted at multiple venues, added to BlueDot's curriculum).

TAAC: Cross-Provider Safety Analysis of Prompt Compression in LLM Inference

Novel safety failure modes discovered across 7 LLM providers with 35,000+ controlled inference trials. Targeting NeurIPS 2026.

AI Security Startup Accelerator Batch #2

Funding 5–10 AI security startups through Seldon’s second SF cohort.

Reducing Risk in AI Safety Through Expanding Capacity.

Get OpenAI employees addicted to factorio

by buying gift cards for the game and handing them out at the OpenAI offices