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

RMR2: 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

Travel grant for attending MI4MedFM workshop at MICCAI

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.

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.

Machine God (documentary film)

Stage 2: pre-registered multi-agent value dynamics test; frontier agents; $1.5k

Gate proves agents engage coupled dynamics before grid spend. Publish-either-way: pass → theory confirmed; fail → clean negative; gate-fail → report.

Karma Ledger benchmark for Agent Governance

Open source, cross-framework benchmark for AI agents

Behavioral Observability for AI Systems in Production

A working infrastructure for auditing AI behavior without access to weights

LivingLoop: The Biological Computing Engine for AI

Forcing living networks of brain cells to act as a self-organizing, ultra-efficient computational substrate that bypasses the GPU scaling trap.

A Pilot for AI-Ready & Biosurveillance-Ready Health Data Infrastructure

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

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

EMILIA Protocol: open authorization receipts for irreversible AI-agent actions

Open, formally-verified proof of which named human approved an irreversible AI-agent action before it ran — so the model isn't the crumple zone.

exist. — measuring and preventing identity drift in generative AI

A governance layer that lets a person refuse AI output that drifts from who they are — and measures the drift. Validated on one case; now scaling to many.

Retroactive: Every Contact Leaves a Trace, a completed interpretability study

A user's engagement style leaves a measurable signature in a language model's attribution graphs. This ask reimburses the completed study's costs.

CKSM: a foundation model architecture derived from neuroscience

Deterministic, constant memory, continuous learning. Building the alternative to transformers

PayBench: A Benchmark for Unsafe Commercial Autonomy

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

SimpleAudit: lightweight, multilingual red-teaming for AI systems anyone can run

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.