问HN：大型语言模型中的时间意识？
我刚刚向ChatGPT发送了一种“功能请求”（但我的问题通常适用于大多数大型语言模型）。
以下是ChatGPT自己写的文本：
*功能请求：* 每个对话/项目的可选时间感知。允许模型接收消息之间的相对经过时间（例如：+5分钟，+4小时，+2天）。这在长时间的叙事、日记、项目跟踪和以关系为导向的对话中尤其有用，因为经过的时间本身具有语义意义。
我主要用它来写日记，而系统完全不意识到如果我与它互动了1小时，下一条消息却在6小时后发送，那么中间发生了一些事情。也许我打盹了。或者可能发生了一些更重大的事情。
我想，不实施这个功能是一个有意识的决定，因为任何客户端都可以发送带有时区的时间，或者决定只有相对时间重要，并通过其他机制提供它。
那么，可能的原因是什么呢？
- 隐私问题？
- 效率（如果我主要使用大型语言模型来获取比谷歌更完整的答案，或者进行情感编码……那么它几乎是无用的）
或者也许是因为这个时间功能会对答案产生过大的影响/消耗更多资源（即使这很微小，如果每个用户的每条消息都有稍微更大的负载或令牌使用，我相信这可能会成为负担）。
出于这两个原因，我会将其配置为用户个人资料/项目/线程级别。但也许我遗漏了其他因素（包括：我们已经回答过这个问题72次，而现在才星期四），这就是我在这里询问的原因。
查看原文
I have just sent a sort of "feature request" to ChatGPT (but my question is generally applicable to most LLMs).<p>Here is the text, written by ChatGPT itself:<p><i>Feature request:</i> Optional temporal awareness per conversation/project. Allow the model to receive relative elapsed time between messages (e.g. +5 min, +4 h, +2 days). This is particularly useful for long-running narrative, journaling, project-tracking, and relationship-oriented conversations where elapsed time itself carries semantic meaning.<p>I mostly use it for journaling, and the fact that the system is completely unaware that if I have interacted with it for 1 hour and the next message comes ... 6 hours later, something happened in between. Maybe I dozed off. Or maybe something more portentous has happened.<p>I suppose that <i>not implementing this</i> was a conscious decision, considering that any client can just send either the time with TZ or decide that only relative time is important and provide it by some other mechanism.<p>So what could be the reason?<p>- privacy concerns?
- efficiency (if I use an LLM mostly to get more complete answers than I can get from Google, or to do vibecoding... then it is pretty much useless)<p>Or maybe it is because this time feature would impact the answers too much/consume more resources (even if this is tiny, if EVERY MESSAGE FROM EVERY USER has a slightly bigger payload or token usage, I am sure it could become a burden).<p>For both reason I would make this configurable at the user profile/project/thread level. But maybe I am missing other elements (including: we have already answered this 72 times and it is only thursday) and this is why I am asking here.