About the Journal

Aim

We have one aim: to identify critical AGI/SI safety work and disseminate it to our target audience via the journal and books derived therefrom.

Scope includes:

  1. AGI/SI safety & value alignment—theory & technology
  2. Progress benchmarks & timing of advent of AGI/SI
  3. Necessary and sufficient conditions for AGI/SI
  4. Databases of all AGI/SI risks; underlying universal principles
  5. Cybersecurity, cyberattacks, cyber deception
  6. Theories of mind, learning, and intelligence; limits of intelligence
  7. Provable or probabilistically guaranteed AGI/SI safety
  8. Validation and verifiability of AGI properties and behavior
  9. AgenticAI, agents, robotics, mixture of experts
  10. Containment methods, guardrails, hardware & software safety tech
  11. Governance
  12. Explainability, Mechanistic Interpretability
  13. World models

Copyright 2025 Kristen W. Carlson