no code implementations • 31 Jan 2024 • Joshua C. Yang, Damian Dailisan, Marcin Korecki, Carina I. Hausladen, Dirk Helbing
This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns.
no code implementations • 31 Jan 2024 • Marcin Korecki
The dominant paradigm in AI ethics and value alignment is highly anthropocentric.
no code implementations • 9 Oct 2023 • Marcin Korecki, Damian Dailisan, Cesare Carissimo
The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives.