Unverified60% confidenceFactExact time
Large language models can hallucinate when generating code, fabricating plausible-sounding but non-existent function names, parameter signatures, or API interfaces.
2
Sources
60%
Confidence
Long-term
Relevance
7/24/2026
First Seen
Sources
Zero-Cost QQ Group Minesweeper Bot in 6 Minutes with DeepSeek
bilibili忘忧嘤7/10/2026
Related Claims
UnverifiedLarge models exhibit hallucination phenomena, fabricating non-existent product terms, calculation formulas, or regulatory rules in an affirmative tone.79% similarVerifiedFor niche domains with insufficient training data, large models tend toward hallucination-based completion, generating API calls, parameter names, or return structures that appear plausible but are actually incorrect77% similarUnverifiedLarge models are stateless; every API call is a completely fresh inference process for the model, relying entirely on the messages list to recall what has previously occurred.76% similarUnverifiedIn code generation scenarios, models may call non-existent APIs, modify functions that should not be touched, or break existing logic without proactively reporting the changes75% similarVerified大模型幻觉是指语言模型生成看似合理但实际不正确或不存在的内容75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/604571API
curl https://kongchang.com/api/v1/knowledge/claims/604571MCP
get_claim(id=604571)