Vol. 1 No. 1 (2024): Artificial General Intelligence Risks, Governance, Methods

					View Vol. 1 No. 1 (2024): Artificial General Intelligence Risks, Governance, Methods

The first issue of AGI focuses on Risks, Governance, and Safety & Alignment Methods. 

Published: 2024-10-09

Articles

  • Highlights of the Issue: Artificial General Intelligence Risks, Governance, Methods

    Kris Carlson
    DOI: https://doi.org/10.70777/si.v1i1.11101
  • The AI Risk Repository A Comprehensive Meta-Review, Database, and Taxonomy of Risks From Artificial Intelligence

    Peter Slattery, Alexander K. Saeri, Emily A. C. Grundy, Jess Graham, Michael Noetel, Risto Uuk, James Dao, Soroush Pour, Stephen Casper, Neil Thompson
    DOI: https://doi.org/10.70777/si.v1i1.10881
  • AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies

    Yi Zeng, Yu Yang, Andy Zhou, Jeffrey Ziwei Tan, Yuheng Tu, Yifan Mai, Kevin Klyman, Minzhou Pan, Ruoxi Jia, Dawn Song, Percy Liang, Bo Li
    DOI: https://doi.org/10.70777/si.v1i1.10863
  • AI Risk Categorization Decoded (AIR 2024) From Government Regulations to Corporate Policies

    Yi Zeng, Kevin Klyman, Andy Zhou, Yu Yang, Minzhou Pan, Ruoxi Jia, Dawn Song, Percy Liang, Bo Li
    DOI: https://doi.org/10.70777/si.v1i1.10603
  • Situational Awareness-Contents-Part IV: The Project

    Leopold Aschenbrenner
    DOI: https://doi.org/10.70777/si.v1i1.11093
  • Soft Nationalization: How the US Government Will Control AI Labs

    Deric Cheng, Corin Katzke
    DOI: https://doi.org/10.70777/si.v1i1.10931
  • Benchmark Early and Red Team Often A Framework for Assessing and Managing Dual-Use Hazards of Ai Foundation Models

    Anthony Barrett, Krystal Jackson, Evan R. Murphy, Nada Madkour, Jessica Newman
    DOI: https://doi.org/10.70777/si.v1i1.10601
  • Acceptable Use Policies for Foundation Models

    Kevin Klyman
    20
    DOI: https://doi.org/10.70777/si.v1i1.10917
  • Against Purposeful Artificial Intelligence Failures

    Roman Yampolskiy
    DOI: https://doi.org/10.70777/si.v1i1.9943
  • Models That Prove Their Own Correctness

    Noga Amit, Shafi Goldwasser, Orr Paradise, Guy N. Rothblum
    DOI: https://doi.org/10.70777/si.v1i1.10867
  • Language-Guided World Models: A Model-Based Approach to AI Control

    Alex Zhang, Khanh Nguyen
    DOI: https://doi.org/10.70777/si.v1i1.10705

Commentary

  • Progress in Superhuman Theorem Proving?

    Steve Omohundro
    DOI: https://doi.org/10.70777/si.v1i1.10947
  • On Yampolskiy, Against Purposeful Artificial Intelligence Failures

    James D. Miller
    DOI: https://doi.org/10.70777/si.v1i1.10703
  • Situational Awareness Part V: Parting Thoughts What If We're Right?

    Leopold Aschenbrenner
    DOI: https://doi.org/10.70777/si.v1i1.11095
  • Unhobbling Is All You Need? On Aschenbrenner’s Situational Awareness

    Ronan McGovern
    DOI: https://doi.org/10.70777/si.v1i1.9945