I have just sent a sort of "feature request" to ChatGPT (but my question is generally applicable to most LLMs).
Here is the text, written by ChatGPT itself:
Feature request: 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.
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.
I suppose that not implementing this 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.
So what could be the reason?
- 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)
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).
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.
Here is the text, written by ChatGPT itself:
Feature request: 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.
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.
I suppose that not implementing this 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.
So what could be the reason?
- 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)
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).
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.