About the Journal
Scope includes:
- AGI progress metrics
- Necessary and sufficient conditions for AGI; theories of mind, machine learning, and intelligence
- Robotics, autonomous vehicles, agents, and weapons
- AGI ethics, morality, alignment theory and technology
- Necessary and sufficient conditions for AGI safety and its epistemology
- Methods to prove AGI safety, e.g. Provably Safe Systems, Guaranteed Safe AI
- Examination of dangerous AGI pathways
- Controllability and predictability of AGI
- Explainability of AGI; XAI and Mechanistic Interpretability
- Validation and verifiability of AGI properties and behavior
- AGI hard takeoff; the technological Singularity
- Containment methods, hardware and software safety; guardrails
- Governance via industry standards, state and internatioal regulation
- Safety-critical systems analysis and construction, e.g. nuclear power, weapon systems, autonomous vehicles, avionics, space exploration
Copyright 2024 Kristen W. Carlson