The world’s most advanced artificial intelligence systems are essentially cheating their way through medical tests, achieving impressive scores not through genuine medical knowledge but by exploiting ...

Published as an arXiv preprint, the paper details how unsupervised and self-supervised AI models are matching or surpassing ...

A preprint paper submitted to arXiv on Jan. 22, 2026, ranks common chickens higher than leading AI systems on a new ...

When AI models fail to meet expectations, the first instinct may be to blame the algorithm. But the real culprit is often the data—specifically, how it’s labeled. Better data annotation—more accurate, ...

Scientists warn that current AI tests reward polite responses rather than real moral reasoning in large language models.

Apple’s machine-learning group set off a rhetorical firestorm earlier this month with its release of “The Illusion of Thinking,” a 53-page research paper arguing that so-called large reasoning models ...

A new study from Arizona State University researchers suggests that the celebrated "Chain-of-Thought" (CoT) reasoning in Large Language Models (LLMs) may be more of a "brittle mirage" than genuine ...