1-month full-time contributing software to Inspect

Support for SAELens and other Decode Research Projects

Preventing AI Catastrophe Through Economic Mechanisms

The Reputation Circulation Standard - Implementation Sprint

Benchmarking and comparing different evaluation awareness metrics

LLMs often know when they are being evaluated. We’ll do a study comparing various methods to measure and monitor this capability.

Cultivating a Mechanistic Interpretability Community

Sustaining and Scaling a Grassroots Research Collective for Neural Network Interpretability and Control

Funding researcher on frontier AI governance inclusive of global majority

Tooling + Model Orgs for CoT Faithfulness Research

Building model organisms of CoT and Python packages for intervention in reasoning traces

Silicon Valley: the Musical

A comedy that gets people thinking about AI in society

TransformerLens - Bridge Funding

AI Safety Los Angeles (AISLA)

The official AI safety community in Los Angeles

Acausal research and interventions

Making sure AI systems don't mess up acausal interactions

Keep Apart Research Going: Global AI Safety Research & Talent Pipeline

Funding ends June 2025: Urgent support for proven AI safety pipeline converting technical talent from 26+ countries into published contributors

The First Actionable Interpretability Workshop at ICML 2025

https://actionable-interpretability.github.io/

Demonstration of LLMs deceiving and getting out of a sandbox

Asterisk AI Blogging Fellowship

'Making God': a Documentary on AI Risks for the Public

Geoffrey Hinton & Yoshua Bengio Interviews Secured, Funding Still Needed

The First Workshop on Mechanistic Interpretability for Vision

Implicit planning in LLMs Paper

Reproducing the Claude poetry planning results quantitatively

Systems that "give a damn"

Teleology, agential risks, and AI well-being

The AI Safety Research Fund

Creating a fund exclusively focused on supporting AI Safety Research