Travel Grant to Present My Mechanistic Interpretability Research at MICCAI 2026

Help an undergraduate mechanistic interpretability researcher present his accepted AI-safety work at MICCAI 2026.

CryptoMind: A Safer AI Agent for TON

An AI agent for crypto and stock analysis with TON token swaps. Every swap must go through user confirmation and fixed safety checks, and the core safety rules

Trace Continuity: Governing AI Memory at Runtime

Trace makes sure an AI has authority before it acts, controls what it is allowed to remember, and checks that authority again before memory is retrieved.

Novel Fine Tuning Academy and Research Initiative

TRiADiC Intelligence Labs ethical alignment research program and consumer empowerment educational program.

The AI Safety Stack

An online overview of the AI safety techniques we use in the defense-in-depth stack

AI Safety Museum - Berlin Pilot

Increasing public awareness of AI risks and benefits through in-person, interactive experiences

Artificial Selves

Integrating Selves and Research on Selves in the AI Community

AI safety for builders hackathon / fellowship

AI safety for builder hackathon / fellowship - to build tools, products, etc.

Belief state geometry of language model personas

A formal, testable account of LLM persona selection as Bayesian inference, validated with model internals, so labs can monitor and steer personas.

Getting Split-Personality Training ready for deployment

Clearing barrieers to adoption for an existing ICML-published interpretability technique that can elicit latent knowledge from red teamed model organisms

Faithful Preference Learning : Cognitively-Aligned Post-Training

This project builds cognitively-aligned preference learning that interprets feedback the way human actually decide rather than as a reward to maximize.

BioRAG-Guard: Poisoning Evals for Biological AI Agents

An open-source benchmark and defense toolkit for testing whether corrupted biological databases can hijack retrieval-augmented AI agents used in genomics, prote

Formalizing mathematical AI safety research in Lean

A hand-verified library of AI-safety theorem statements in Lean 4 with AI-generated proofs, building the skills to trust AI formalization.

Fund development of p(Doom)1

A nightmarishly hard AI safety strategy game about holding p(Doom) down. You can't win; you can only buy time.

Help the Argentinian AI Safety Community Grow

The Argentinian AI Safety community (BAISH, baish.com.ar) is the largest in Latin-America. Support BAISH's growth, by providing funding for paying salaries.

Separatrix

Creating conditions for cooperative strategies to dominate adversarial ones among near-future AIs while we still can

Evaluating the Tacit Coordination Capacity and Decision Theory of LMs

A benchmark to empirically investigate: (i) the ability of models to tacitly coordinate with copies of themselves and (ii) which decision theory best explains t

Formally verified autoresearch for theoretical mech interp

LLM agents collaborate to discover and formally verify theorems about the internal computations of transformers, beginning with a simple pilot question: how man

Testing Human Adjudication as a Backstop Against Correlated AI Failures

Interpreting Latent Reasoning Models with Natural Language Autoencoders