我发现跟大模型聊天特别累，我分析了一下，原因大概有三点：
一个是它回答太啰唆。我说一句，它回八句半，还顺手把我没问的一起答了。
一个是它老省略宾语。经常省掉一两个字，我经常看了半天才反应过来。
一个是它不喜欢重复。上一秒说完强化学习，下一秒就忘了这个名词，又换个新说法。
过度联想、思维跳跃、用词求新
有点像那种说话喜欢掉书袋的家伙
Chatting with large models feels tiring for three reasons
AISummary
The author finds chatting with LLMs exhausting due to three traits: verbose answers that add unasked content, frequent omitted objects that require rereading, and avoiding repeated terms by switching to new wordings. The post likens the behavior to a pedantic person who overuses obscure phrasing and jumps between associations.
Post on XView on X
@oran_ge
Source: Orange AI · x.comPublished · added here