Physics-Governed Memory for Auditable AI

Building a physics-governed memory system that makes long-term AI behavior auditable and resistant to deceptive alignment.

Ambitious AI Alignment Seminar

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

Department of Future Listening: Narrative Risk Radar (UK pilot)

Detect polarising story-frames early and build better narratives—fast, practical, adoptable.

Evitable: a new public-facing AI risk non-profit

Our mission is to inform and organize the public to confront societal-scale risks of AI, and put an end to the reckless race to develop superintelligent AI.

Forethought

Research on how to navigate the transition to a world with superintelligent AI systems

Reducing Risk in AI Safety Through Expanding Capacity.

AI Security Startup Accelerator Batch #2

Funding 5–10 AI security startups through Seldon’s second SF cohort.

Paper Clip Apocalypse (War Horse Machine)

Short Documentary and Music Video

Terminal Boundary Systems and the Limits of Self-Explanation

Formalizing the "Safety Ceiling": An Agda-Verified Impossibility Theorem for AI Alignment

Public Food Procurement as a Climate Policy Tool in the EU

Assessing the Climate Potential of Catering Systems in Public Schools and Hospitals

Addressing Agentic AI Risks Induced by System Level Misalignment

AI Safety Camp 2026 project: Bidirectional Failure modes between security and safety

Runway till January: Amplify's funding ask to market EA & AI Safety 

Help us solve the talent and funding bottleneck for EA and AIS.

Offensive Cyber Kill Chain Benchmark for LLM Evaluation

Measuring whether AI can autonomously execute multi-stage cyberattacks to inform deployment decisions at frontier labs

Testing a Deterministic Safety Layer for Agentic AI (QGI Prototype)

A prototype safety engine designed to relieve the growing AI governance bottleneck created by the EU AI Act and global compliance demands.

AURA Protocol: Measurable Alignment for Autonomous AI Systems

An open-source framework for detecting and correcting agentic drift using formal metrics and internal control kernels

SDCPNs for AI Safety

Developing correct-by-construction world models for verification of frontier AI

Disentangling Political Bias from Epistemic Integrity in AI Systems

An Integrative Framework for Auditing Political Preferences and Truth-Seeking in AI Systems

Guaranteed Safe AI Seminars 2026

Seminars on quantitative/guaranteed AI safety (formal methods, verification, mech-interp), with recordings, debates, and the guaranteedsafe.ai community hub.

The Deal of the Century (for AI)

Persuading a critical mass of key potential influencers of Trump's AI policy to champion a bold, timely and proper US-China-led global AI treaty

Shallow Review of AI Governance: Mapping the Technical–Policy Implementation Gap

Identifying operational bottlenecks and cruxes between alignment proposals and executable governance.