Unverified50% confidenceSolutionExact time
在提示词中要求模型简短无法降低输入成本，因为上下文在读取提示词之前就已发送
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Local Code Indexing: Cutting AI Coding Token Costs by 94%
bilibiliAIToBox6/30/2026
Related Claims
Unverified提示词工程无需修改模型权重，仅凭文本指令即可实现任务切换69% similarUnverified文本分类、简单摘要、意图识别等任务可由更小更便宜的模型胜任，无需调用旗舰模型67% similarUnverifiedModels in the 2B parameter range are suitable for lightweight tasks such as simple question answering, text summarization, and code completion, and are not suitable for complex reasoning or long-text understanding.66% similarUnverifiedThe output of large language models is fundamentally probabilistic text generation, and a single rephrasing of a prompt can change field names, nesting levels, or enumeration values in the output without triggering compile-time or static analysis warnings.66% similarUnverified提示词注入分为直接注入和间接注入两种形式，因语言模型无法区分数据与指令，凡进入上下文窗口的文本都可能被执行65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/491011API
curl https://kongchang.com/api/v1/knowledge/claims/491011MCP
get_claim(id=491011)