And the retrieval models are powerful, but they're a lot less powerful than a modern LLM.
检索模型很强大,但它们比现代大语言模型弱得多。
来源:How Intercom Cut $250K/Month by Ditching GPT for Open Models | Fergal Reid · Chain of Thought — host and credited guests章 t-3段 sentence:00fc3accc4ef924677e0d287Chain of Thought — chainofthought.show; https://chainofthought.show/podcast/49-how-intercom-cut-250k-month-by-ditching-gpt-for-qwen/; CC BY 4.0 https://creativecommons.org/licenses/by/4.0/ ; selection/segmentation by SharedEnglishCorpus. Audio not licensed.