AI: Unexplainable, Unpredictable, Uncontrollable
Roman V. Yampolskiy. CRC Press / Chapman & Hall, Artificial Intelligence and Robotics Series, February 2024, 250 pp. [publisher]
AI: Unexplainable, Unpredictable, Uncontrollable Read More »
AI-Safety
Of Models and Tin Men: Principal-Agent Problems in AI Alignment
Steve Phelps, Rebecca Ranson. “Of Models and Tin Men: A Behavioural Economics Study of Principal-Agent Problems in AI Alignment using Large-Language Models”. arXiv:2307.11137, July 2023 [preprint]
Of Models and Tin Men: Principal-Agent Problems in AI Alignment Read More »
Unethical Research: How to Create a Malevolent Artificial Intelligence
Sapience Technical Report STR 2016-03 Author: Roman V. Yampolskiy Cybersecurity research involves publishing papers about malicious exploits as much as publishing information on how to design tools to protect cyber-infrastructure. It is this information exchange between ethical hackers and security experts, which results in a well-balanced cyber-ecosystem. In the blooming domain of AI Safety Engineering, hundreds
Unethical Research: How to Create a Malevolent Artificial Intelligence Read More »