Heuristics and Biases in AI Decision-Making: Implications for Responsible AGI

Payam Saeedi, Mahsa Goodarzi, M Abdullah Canbaz

We investigate the presence of cognitive biases in three large language models (LLMs): GPT-4o, Gemma 2, and Llama 3.1. The study uses 1,500 experiments across nine established cogn…