welcome
Live Science

Live Science

Technology

Technology

AI is just as overconfident and biased as humans can be, study shows

Live Science
Summary
Nutrition label

82% Informative

ChatGPT exhibited many of the most common human decision-making biases in almost half of the scenarios examined in a new study.

Authors from five academic institutions across Canada and Australia tested OpenAI 's GPT-3.5 and Gpt-4.

The study concluded that the biases shown weren't just a product of memorized examples — but part of how AI reasons.

VR Score

84

Informative language

86

Neutral language

17

Article tone

informal

Language

English

Language complexity

66

Offensive language

not offensive

Hate speech

not hateful

Attention-grabbing headline

not detected

Known propaganda techniques

not detected

Time-value

medium-lived

Affiliate links

no affiliate links