Unverified50% confidenceFactExact time
Claude在使用扩展思考功能时其内部推理链条对用户部分不可见，OpenAI的o1模型同样如此
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/25/2026
First Seen
Valid until: 11/23/2026
Sources
Related Entities
Related Claims
UnverifiedOpenAI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% similarUnverifiedOpenAI 推出了 o1、o3 系列推理模型，Anthropic 在 Claude 中引入了 extended thinking 功能，Google Gemini 也提供了类似能力71% similarUnverifiedThe OpenAI o1 series uses implicit CoT (thinking tokens), where the reasoning process is invisible to users but still consumes computational resources.69% similarUnverifiedClaude使用Human/Assistant对话格式，而OpenAI模型使用System/User/Assistant三段式结构68% similarUnverifiedOpenAI's o1 series deliberately conceals the complete original chain of thought and only provides a summarized version, with the official rationale involving safety alignment and preventing it from being used to distill competing models.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/797960API
curl https://kongchang.com/api/v1/knowledge/claims/797960MCP
get_claim(id=797960)