Unverified50% confidenceFactExact time
The frequent use of em-dashes is one of the most prominent linguistic features of LLM-generated text
1
Sources
50%
Confidence
Long-term
Relevance
8/14/2026
First Seen
Sources
认知负债：当开发者外包了自己的思考
Related Claims
UnverifiedLlama 3 的词表扩展使得非英语文本（特别是使用非拉丁字母的语言）的编码效率提升约 30-40%70% similarUnverifiedLLMs acquire language capabilities by performing unsupervised pre-training on massive text corpora (predicting the next token).66% similarUnverifiedLLM 在处理语法错误、拗口句式、被动语态滥用、冗余表达等表层语言问题上表现出色，能在几秒内给出流畅的改写建议63% similarUnverifiedLarge language models fall into two major categories: Base LLMs and Instruction Tuned LLMs.62% similarUnverifiedLarge language models (LLMs) rely on two key capabilities—natural language understanding (NLU) and intelligent content generation (NLG)—to implement conversational functionality.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/745180API
curl https://kongchang.com/api/v1/knowledge/claims/745180MCP
get_claim(id=745180)