https://www.quantamagazine.org/is-ai-reasoning-right-for-the-wrong-reasons-20260731/
Is AI Reasoning Right for the Wrong Reasons?
John Pavlus
July 31, 2026
"His working hypothesis is that an LRM... performs what he calls “approximate retrieval” across its vast training corpus: “somewhere in the middle” between pattern matching and reasoning... The role of “thinking tokens,” then, isn’t to narrate an actual chain of thought..."