Ars Technica@arstechnica@mastodon.social
Researchers find LLMs are bad at logical inference, good at “fluent nonsense”
Chain-of-thought AI "degrades significantly" when asked to generalize beyond training.
https://arstechnica.com/ai/2025/08/researchers-find-llms-are-bad-at-logical-inference-good-at-fluent-nonsense/?utm_brand=arstechnica&utm_social-type=owned&utm_source=mastodon&utm_medium=social
