Unverified50% confidenceFactExact time
Hidden Chains of Thought do not require explicitly displaying each step of the thinking process in the output, allowing the model to perform reasoning iterations within its internal state space.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedResearch has found that the chain-of-thought reasoning generated by models does not fully correspond to their actual internal computation processes, and may provide post-hoc explanations unrelated to the true decision-making path.79% similarUnverifiedCOCONUT (Chain of Continuous Thought) propagates the reasoning chain directly in continuous latent space, feeding the hidden state produced by the previous reasoning step directly as input to the next, bypassing the encode-decode loop from hidden state to token and back to hidden state.77% similarUnverifiedChain-of-Thought 的推理链完全在模型内部展开，无法感知外部状态变化76% similarUnverifiedThe 'deep thinking mode' feature, where a model performs an internal Chain of Thought before generating a final answer, does exist in some official AI models76% similarUnverifiedWhen large language models generate code, they form a Chain of Thought, and subsequent self-checks tend to follow the same reasoning path, making it difficult to break out of the existing logical framework to identify blind spots.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/904641API
curl https://kongchang.com/api/v1/knowledge/claims/904641MCP
get_claim(id=904641)