A Mathematical Framework for Interpretable AGI via Analog Wave Interference

Phase 1

First paper on governing automated OSINT and scoping an institutional home

LLMs could automate intelligence analysis. I wrote the first paper on governing this; $5k buys 2mo to revise it and scope an org research branch

Systematic Probing of Exploit Chains and Governance in Multi-Agent Tool

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

We're a team building World-Model-Lens, a library for Interpretability

Observability and interpretability toolkit for world models in AI safety and mechanistic interpretability research.

Benchmarking Deceptive Improvement in Agentic Systems

An open-source safety pilot for detecting metric gaming, pseudo-improvement, and oversight evasion

Safe AI Germany (SAIGE)

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

Support for Attending ICLR 2026 conference to present 2 posters

AI Readiness Objectives for AGI Preparedness

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

Towards Shared AI Compute Infrastructure

Hypothesis Prism: A Structural Representation Layer for Scientific Experiments

LLMs scale language, not method. HP turns hypothesis-driven papers into machine-readable maps of variables, controls, stats, and findings for researchers & AI.

SOPHIA: Open-Source Epistemic Constitution for AI Reasoning

An executable reasoning quality framework that checks whether AI-generated arguments are logically sound — not just factually accurate. Live at usesophia.app.

AI Security Startup Accelerator Batch #2

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

Law School for AI Governance

Support my postgraduate law studies and research in AI Governance

Job Security Compass

An Interactive Tool for Navigating AI Career Risk

Fund thebes' model tinkering

Research, tutorial writing, and open-source libraries & tools for experimenting with language models

Formal Certification Technologies for AI Safety

Developing the software infrastructure to make AI systems safe, with formal guarantees

FloraForge: Aesthetic Gene Editing in Petunias

A modular gene-editing platform for engineering new pigment patterns in ornamental plants, starting with a vein-pattern rescue line in petunias.

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 :)

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.

[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).