Unverified50% confidenceFactExact time
After reasoning models such as DeepSeek-R1 and Qwen3 pushed chain-of-thought training to its extreme, side effects emerged including the model repeatedly self-verifying, frequently backtracking, and generating large amounts of inner monologue on simple questions.
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedModels such as o1 and DeepSeek-R1 internalize chain-of-thought as a training objective, generating a large amount of internal draft reasoning before producing the final answer.80% similarUnverifiedReasoning-enhanced models (such as o1 and DeepSeek-R1) consume large numbers of reasoning tokens in their chain-of-thought process that are invisible to users; the actual tokens consumed by o1-preview are often 3 to 8 times that of the visible output.73% similarUnverifiedThe overthinking problem is not unique to Qwen3; reasoning models such as DeepSeek-R1 and the OpenAI o1 series all exhibit similar phenomena to varying degrees.73% similarUnverified一些推理增强型模型（如DeepSeek-R1、Kimi K3）会生成非常长的思维链，有时推理过程的Token数量是最终答案的数十倍73% similarUnverifiedDeepMind's Chinchilla scaling law demonstrates that the optimal ratio of training data volume to model parameter count evolves over time, and equal FLOP investment can produce models with significantly different capabilities72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/930259API
curl https://kongchang.com/api/v1/knowledge/claims/930259MCP
get_claim(id=930259)