AI Safety Hong Kong (AISHK)

Agent limits that survive delegation

When an AI agent spawns sub-agents, its safety limits do not follow. I build and deploy the layer that makes them inherited and non-strippable.

Sentient Futures Project Incubator

Funding compute/API costs for Incubator projects that build nonhuman welfare consideration into AI safety work

safely.bio: Customer screening for DNA synthesis providers

Deploying customer screening software at DNA synthesis providers to reduce AI-enabled biothreats

Evaluating the safety, ethics, and values of quantized and finetuned open models

Help me evaluate the safety, ethics, and values of the quantized and fine-tuned open-weight LLMs that individuals and enterprises are actually using.

Reading China's AI Registry: A Public Monitor

Monthly analysis of China's algorithm-filing registry and binding AI security standards, read in Chinese, for the people calibrating AI rules in the West.

US Policy Communication Playbook for an AI Crisis

A playbook to help AI safety policy advocates communicate with the U.S. government during the window of opportunity during an AI-related crisis.

La P8stée: a 28-minute AI-risk film in the tradition of La Jetée

It's an arthouse horror film. It's got a girl and a gun and global catastrophic risk.

Separatrix

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

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.

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.

Supplementing Summer Program for Applied Rationality and Cognition 2026 (SPARC)

Frontier AI Election Evaluation Framework

A practical evaluation framework to identify governance failures in frontier AI systems during elections.

Testing Human Adjudication as a Backstop Against Correlated AI Failures

Flourishing Futures Fellowship

A scalable fellowship training researchers to develop interventions for achieving high-value long-term futures

Postdoc on verification protocols for frontier AI training

Low-overhead zero-knowledge proofs of properties of training

Frontier AI — No Sheriff in Town

A research bridge to safer deployment

BASE Technical AI Safety Training Initiative

Providing GPU credits and instructional support for 40 participants completing the ARENA AI Safety curriculum through Black in AI Safety and Ethics (BASE)

Mechanistically estimating the outputs of wide random convolutional neural nets

Beyond single-agent safety: Training LLM agents to cooperate

Reinforcement learning for cooperative LLM agents to address multi-agent risks.