Unverified50% confidenceDecision RuleExact time
The model selection principle is: use chat models for simple tasks, use reasoning models for complex tasks, and match based on task capability and cost.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
VerifiedIn the standard large language model interaction architecture, the system prompt is injected into the model's context at the beginning of each conversation to define the model's role, behavioral boundaries, and task rules.78% similarVerifiedTypical tiered routing logic assigns simple tasks to small, inexpensive models, intermediate tasks to mid-tier models, and complex tasks to flagship-level models.78% similarUnverified模型直觉包括判断任务是否需要 RAG、Agent 多步推理或微调等技术路径的选择能力77% similarUnverifiedChain-of-Thought prompting encourages the model to reason step by step, few-shot prompting helps the model understand the task format by providing examples, and System Prompts are used to set the model's role and behavioral constraints.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/997568API
curl https://kongchang.com/api/v1/knowledge/claims/997568MCP
get_claim(id=997568)