The Enduring Path to Alignment: Inorganic Existential Social Theory

WithMe Test Case 001

Help Sue Private Intelligence Firms Hitting AI Whistleblowers

Seen & WithMe

Keep AI Whistleblowers Alive

Philosium Tokyo 9/19/2026

1-day EA x Philosophy event for high school and university students at the University of Tokyo

Guided Symbiosis: Stress-Testing a Third-Layer AGI Safety Architecture

Making human survival part of the system’s optimal strategy—not merely another constraint.

Establishing an AI Risk Communication for Public Preparedness Framework

There's an asymmetry between the level of communication about AI capabilities, compared to AI risks. If we hit AGI tomorrow, the world would not be prepared.

deathbench.com - open data on real world ai-caused deaths

Documenting deaths caused by ai.

Volta Education Suite: AI Risk Engine (VES:ARE)

Facilitating AI X-risk Education in India, Southwest Cameroon, and beyond!

Research on AI Safety in Agriculture on Hallucination and Evaluation

An open-source study of AI safety, dialect accuracy, and hallucination in farming contexts.

AI Safety Hong Kong (AISHK)

Prediction of Inoculation Prompt Side Effects

An open, cheap method that detects when an inoculation prompt inoculates against off-target traits, so labs and developers can catch undesired trait/persona cha

Threat Models for AI-Enabled Crisis Instability

Detailed models of how delegating critical functions to AI agents could destabilise strategic stability: pathways, likelihoods, and defenses.

Funding support to attend PauseCon London 2026

Sentient Futures Project Incubator

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

ILINA Junior Research Fellowship

A junior research fellowship for recent African graduates that combines ILINA’s spring seminar with a mentored research phase on AI and global catastrophic risk

Frontier AI Election Evaluation Framework

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

safely.bio: Customer screening for DNA synthesis providers

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

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.

Separatrix

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

Defining dangerous DNA with the Sequence Biosecurity Risk Consortium (SBRC)

Defining which sequences are dangerous enough to screen for, so providers and regulators screen consistently