Observatoire des droits humains (anglais seulement)

AI systems are great at tests. But how do they perform in real life?

(Version anglaise seulement)

par Peter Douglas, Lecturer, Monash Bioethics Centre, Monash University

Earlier this month, when OpenAI released its latest flagship artificial intelligence (AI) system, GPT-5, the company said it was “much smarter across the board” than earlier models. Backing up the claim were high scores on a range of benchmark tests assessing domains such as software coding, mathematics and healthcare.

Benchmark tests like these have become the standard way we assess AI systems – but they don’t tell us much about the actual performance and effects of these systems in the real world.

Lire l'article complet