Unverified60% confidenceFactExact time
The OpenAI o1 series uses implicit CoT (thinking tokens), where the reasoning process is invisible to users but still consumes computational resources.
2
Sources
60%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
UnverifiedOpenAI的o1系列模型的reasoning tokens对用户不可见80% similarUnverifiedA single complex reasoning task with OpenAI's o1-pro can generate tens of thousands of hidden thinking tokens, and the cost may be 5–10 times that of normal mode.77% similarUnverifiedOpenAI在o1的技术说明中表示，出于对齐监控和避免用户被未经对齐的原始想法误导的考虑，不会向用户直接展示完整的原始思维链75% similarVerifiedOpenAI's o1 model was released in September 2024; through reinforcement learning it was trained to perform internal reasoning before outputting a final answer, with intermediate reasoning steps existing as special tokens that are invisible to users.71% similarUnverifiedOpenAI的o1模型仅展示经过处理的'思考摘要'而非原始推理token，而谷歌AI Studio则提供相对更完整的内部推理可见性69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/546984API
curl https://kongchang.com/api/v1/knowledge/claims/546984MCP
get_claim(id=546984)