18:12
2026-06-27
letsdatascience.com
large-language-models
Critics Highlight AI Failures on Simple Tasks
A peer-reviewed PNAS Nexus study found that leading large language models, including GPT-4o, Claude 3.5 Sonnet, GPT-5, Claude Opus 4.1, and Gemini 2.5, fail catastrophically on simple cognitive tasks …