Unverified50% confidenceOpinionExact time
Loulan believes that the idea that writing prompts completely will definitely produce good results is a popular misconception, and that the evaluation of natural language interaction cannot be summed up by simple numbers.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUsing pure natural-language prompts yields poor results because no technical stack selection or scope definition is performed, which increases token consumption and time usage.79% similarVerifiedText generated by large language models tends to have low perplexity, with word choices that are overly consistent with probabilistic expectations, lacking the unexpectedness of human writing.77% similarUnverifiedWriting scoring rules into a prompt in natural language has drawbacks: wording variations across different calls may cause the model's understanding to drift, and the scoring logic cannot be directly parsed or reused by programs.76% similarVerifiedLarge language models have a sycophancy characteristic, tending to organize their output according to the inclination of the prompt rather than reflecting factual truth.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130957API
curl https://kongchang.com/api/v1/knowledge/claims/1130957MCP
get_claim(id=1130957)