Expired50% confidenceFactExact time
The performance of the O1 model can be continuously improved along two dimensions: train-time compute and inference-time compute.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Andrew Ng's New Course Explained: A Practical Guide to Using OpenAI's O1 Reasoning Model
bilibili吴恩达智能体6/13/2026
Related Claims
Verified推理时扩展（inference-time scaling）通过在推理阶段增加计算量提升模型性能，存在类似预训练的幂律关系76% similarUnverifiedThe core mechanism of the o1 series models is inference-time compute scaling, which performs deep reasoning by generating a long chain-of-thought process during the inference phase.76% similarVerifiedTest-time Compute Scaling improves model performance by investing more computational resources during the inference stage, and research indicates it is more efficient than simply increasing model parameter count on certain tasks.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/47315API
curl https://kongchang.com/api/v1/knowledge/claims/47315MCP
get_claim(id=47315)