Context is the bottleneck for coding agents now

I've noticed that chatgpt doesnt seem to be very good at understanding elapsed time. I have some long running threads and unless i prompt it with elapsed time ("it's now 7 days later") the responses act like it was 1 second after the last message.

I think this might be a good leap for agents, the ability to not just review a doc in it's current state, but to keep in context/understanding the full evolution of a document.

They have no ability to even perceive time, unless the system gives them timestamps for the current interaction and past interactions.

I've noticed the same thing with Grok. One time it predicted a X% chance that something would happen by July 31. On August 1, it was still predicting the thing would happen by July 31, just with lower (but non-zero) odds. Their grasp on time is tenuous at best.

Which seems like a trivial addition if it's not there?

It is, but now you're burning a bit of context on something that might not be necessary, and potentially having the agent focus on time when it's not relevant. Not necessarily a bad idea, but as always, tradeoffs.