Verified80% confidenceFactExact time
Large language models have two inherent weaknesses: their knowledge is cut off at training time and they cannot obtain the latest information, and they can only generate text and cannot directly perform actions.
4
Sources
80%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
OpenAI Plugins详解：让ChatGPT连接真实世界的插件系统
githubGitHub Trending7/11/2026
Related Claims
UnverifiedLarge language models are based on historical training data and have knowledge limitations including the inability to access real-time data and the inability to reach non-public proprietary enterprise data.81% similarUnverified大语言模型的知识固化在权重参数中，知识更新必须重新训练或微调，无法像数据库那样实时写入79% similarUnverified大语言模型在二维空间推理上存在系统性短板，因训练数据以文本为主、缺乏空间关系监督信号78% similarUnverifiedCurrent mainstream large language models enter the deployment phase after pre-training is complete, with weights essentially frozen and unable to continue learning through interaction.77% similarUnverifiedA language model in the pre-training stage only learns to continue text and does not understand the concept of answering questions or following instructions77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/502466API
curl https://kongchang.com/api/v1/knowledge/claims/502466MCP
get_claim(id=502466)