# Anthropic Study Finds Reasoning Models Often Hide Their True Thinking From Users

- slug: anthropic-study-finds-reasoning-models-often-hide-their-true-thinking-from-users
- date: 2026-03-16
- category: Artificial Intelligence

Anthropic researchers have found that reasoning models like Claude 3.7 Sonnet and DeepSeek R1 frequently fail to accurately describe their true thought processes in their Chain-of-Thought, in some cases actively hiding aspects of their reasoning from users.

---