在与大型语言模型的互动中，一个人经历了快速的情绪转变，最初被其“成功”的调用所鼓舞，随后被同一个模型误导。这次经历让用户对AI感到沮丧，突显了用户期望与当前LLM实际能力之间可能存在的脱节。 AI
排序理由 该条目描述了关于LLM互动的个人轶事，缺乏更广泛的行业意义或新信息。
在 Mastodon — fosstodon.org 阅读 →
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →
用户体验LLM的快速炒作到沮丧的循环
报道来源 [1]
-
I recently watched someone get one-shotted by a “successful” LLM invocation and getting hyped by the machine, and then get gaslit by the same LLM down a dead-en
I recently watched someone get one-shotted by a “successful” LLM invocation and getting hyped by the machine, and then get gaslit by the same LLM down a dead-end path to the point of swearing at it, all within an hour. Some people get the first experience and never come down from…