Vol. 2 No. 2 (2025): Large Language Models II

Red-teaming evaluation. Lifelong attack integration.

Given the critical point in time we face on AI governance, the third issue of SuperIntelligence features articles, reviews, and an editorial on AI governance. We continue to examine safety & value alignment, especially of Large Language and foundation Models. A new feature is a collection of AI-generated reviews of key papers.

Published: 2025-05-29

Articles

  • Highlights of the Issue: Large Language Models II

    Kris Carlson
    DOI: https://doi.org/10.70777/si.v2i2.14909
  • The First International AI Safety Report The International Scientific Report on the Safety of Advanced AI

    Yoshua Bengio
    DOI: https://doi.org/10.70777/si.v2i2.14755
  • A Framework for the Private Governance of Frontier Artificial Intelligence

    Dean Ball
    DOI: https://doi.org/10.70777/si.v2i2.14519
  • LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures

    Franciso Aguilera-Martinez, Fernando Berzal
    DOI: https://doi.org/10.70777/si.v2i2.14441
  • AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

    Andy Zhou, Kevin Wu, Francesco Pinto, Zhaorun Chen, Yi Zeng, Yu Yang, Shuang Yang, Sanmi Koyejo, James Zou, Bo Li
    DOI: https://doi.org/10.70777/si.v2i2.14433
  • Pitfalls of Evidence-Based AI Policy

    Stephen Casper, David Krueger, Dylan Hadfield-Menell
    DOI: https://doi.org/10.70777/si.v2i2.14611
  • Strategic Patience: Long-Horizon AI Dominance and the Erosion of Human Vigilance

    Roman Yampolskiy
    DOI: https://doi.org/10.70777/si.v2i2.14435
  • Quantum Immortality A Perspective If AI Doomers Are Probably Right

    Alexey Turchin, James Miller
    DOI: https://doi.org/10.70777/si.v2i2.14439

Editorials

  • The Perilous State of AI Governance, June 2025

    Kris Carlson
    DOI: https://doi.org/10.70777/si.v2i2.14801

Commentary

  • California Senate Bill 813: A Novel Approach to Artificial Intelligence Governance

    Kristen W Carlson
    DOI: https://doi.org/10.70777/si.v2i2.14571

Reviews