Making sure that the code AI pushes to the internet is safe and bug-free

Building LemmaScript, a verification toolchain for TypeScript

Mechanistic repair of cross-lingual safety failures with SAE-Aware refusal steer

Safety steering that actually works off English

Finding and Defending the Attention Circuits That Make LLMs Jailbreakable

Mapping the attention heads that push LLMs toward refusal vs. compliance, and building an inference-time defense against both single- and multi-turn jailbreaks.

mirror - the sub-Turing compiler for local, decidable inference

Mirror is a programming language written BY AI FOR AI and written FOR HUMANS BY HUMANS.

Depolarization in democratic mechanisms

A study to empirically study the depolarization effect of our values elicitation method

Pax Machina

A publication about the institutions we need for powerful AI.

Testing Endogenous Reconstruction in a Distributed Sensorimotor Architecture

Can a Distributed Sensorimotor System Reconstruct Without External Stimulus?

Travel grant to attend HAAISS Prague 2026

Why Do All Materials Move Inside an Energized Magnetic Core?

This motion affects everything. Since only gravity can move all objects, this anomaly could unlock the secret to artificial gravity control.

Observer Stabilization and Coherence in Coupled Human–AI Systems

AI Safety Roster: a searchable directory of everyone in AI safety

A fast, comprehensive directory of the people and orgs in AI safety: search, filter, and match.

Machine God (documentary film)

ICML Travel & Independent Research Bridge

Compositional Learning Behaviours as a Necessary Condition for Olympiad-Level Formal Theorem Proving

Travel funding for DL4C at ICML Workshop 2026

LEVF: Searching for Synergies in Rejuvenation Biotechnology

The Longevity Escape Velocity Foundation (LEVF) seeks support for one of the most neglected and potentially important questions in aging research

Ndome — zero-trust, mechanically-verifiable safety scoring for AI agents

An independent safety score for AI agents you can verify — deterministic, reproducible, auditable, and it never needs your private data.

Travel grant for attending MI4MedFM workshop at MICCAI

PayBench: A Benchmark for Unsafe Commercial Autonomy

Benchmark for agent safety when spending users money. How often do they violate user intent and rules?

DriftBench v1.1: an ambivalence metric + 20 cross-domain scenarios

Deterministic, no-LLM-judge benchmark for how faithfully AI tracks changing beliefs. Funding v1.1: a new ambivalence metric + 20 cross-domain scenarios.

ICML Workshop Travel: Cross-Constitution Drift in LLM Character Training

Accepted ICML 2026 workshop paper on cross-constitution drift in LLMs; seeking $2,050 travel support to present in Seoul and gather research feedback.