Career Transition into AI Control after Postdoc

Emergent misalignment and memetic replication in multi-agent codebases

The History of AI as X-risk

Designing a Project Funding Proposal

Support for Research on Presenting Full Paper at AAMAS 2026

Investigate how LLMs behave in multi-agent environments particularly how contextual framing and strategic advice can systematically manipulate coord. outcomes

Human-AI Complementarity for Identifying Harm

Make AI Safe Worldwide: Infrastructure for Governing Advanced AI at Global Scale

Runtime safety, oversight, rollback, and control infrastructure for advanced AI in real-world, high-consequence environments.

DystopiaBench

A Safety Framework for Evaluating AI Humanity Alignment Through Progressive Escalation and Scope Creep

Safe AI Germany (SAIGE)

Germany’s talents are critical to the global effort of reducing catastrophic risks brought by artificial intelligence.

AI Risk Literacy Infrastructure for Preventing Misuse of Advanced AI Systems

Could RLHF Accidentally Select for Deception?

An experiment testing whether RLHF training could create selection pressure favoring deceptive AI outputs over honest ones.

Mitigating Reward Hacking Through RL Training Interventions

ClinSafe: The Missing Safety Net for Medical AI

An open platform to stress-test how LLMs handle bias, pressure points, and clinical decisions. Built on peer reviewed real evidence.

12th Edition of AI Safety Camp

Seed Funding For Geodesic Research

Agent Island: An Environment for Interagent Cooperation and Conflict

A flexible simulation environment for assessing strategic and persuasive capabilities, benchmarking, and agent development, inspired by reality TV competitions.

Ambitious AI Alignment Seminar

One Month to Study, Explain, and Try to Solve Superintelligence Alignment

Help a Bootstrapped AI Risk Literacy Founder Get To IASEAI 2026 in Paris

Nutrition labels transformed food safety through informed consumer choice, help me do the same for AI and make this standard :)

Hypothesis Prism: A Structural Representation Layer for Scientific Experiments

LLMs scale language, not method. HP turns hypothesis-driven papers into machine-readable maps of variables, controls, stats, and findings for researchers & AI.

AI Crisis Convening at India AI Impact Summit 2026

Translating in-person convening to measurable outcomes

Compassion Bench

Open Welfare Alignment Evals for Frontier Models