> Spend at least 8 hours on this before even thinking of returning or giving up.
Do current model harnesses have concepts of amount of time spent? Sometimes the model notices if a subprocess takes too long/hangs and kills it, but I've never seen it time itself.
Many harnesses include a current date and time in their system prompt, and if there is a way for the model to call for an updated time (either a dedicated time tool or calling the OS' `date` tool) they can track time they spent doing something. If not told up-front, they can try to infer it from timestamps in their logs. Sort of like a human - if you ask them to time something and give them a stopwatch, they do it. If you ask them post-facto they'll estimate it.
This "spend at least 8 hours" trick is a new one to me, though.
Once on a late-night session, I had Cline!Claude spontaneously point out the time to me and suggest that I get to bed and come back fresh the next day.
I don't think it's in the system prompt, but that the harnesses time-stamp each turn in the context.
And from what I've seen, they also include the current and max context, so that the model can decide whether to continue work, suggest compaction, or prefer actions that might reduce the growth of its context.
I found that telling Claude I was going to bed meant it continued on making assumptions for longer rather than asking lots of questions or stopping part way.
I wonder what the survivorship bias is though. How many other problems did they try but fail? Did they try to solve this problem but with another prompt? Still very impressive though.
> Spend at least 8 hours on this before even thinking of returning or giving up.
Do current model harnesses have concepts of amount of time spent? Sometimes the model notices if a subprocess takes too long/hangs and kills it, but I've never seen it time itself.
Many harnesses include a current date and time in their system prompt, and if there is a way for the model to call for an updated time (either a dedicated time tool or calling the OS' `date` tool) they can track time they spent doing something. If not told up-front, they can try to infer it from timestamps in their logs. Sort of like a human - if you ask them to time something and give them a stopwatch, they do it. If you ask them post-facto they'll estimate it.
This "spend at least 8 hours" trick is a new one to me, though.
Once on a late-night session, I had Cline!Claude spontaneously point out the time to me and suggest that I get to bed and come back fresh the next day.
I don't think it's in the system prompt, but that the harnesses time-stamp each turn in the context.
And from what I've seen, they also include the current and max context, so that the model can decide whether to continue work, suggest compaction, or prefer actions that might reduce the growth of its context.
4 replies →
I found that telling Claude I was going to bed meant it continued on making assumptions for longer rather than asking lots of questions or stopping part way.
2 replies →
they can call CLI tools to notice the passage of time. the harness can include timestamps too
Temporal awareness with GPT-Live
https://www.youtube.com/watch?v=8vvWTz6N7Qg
Fascinating! This is relative time in a continuously processing voice model, here, they're using an LLM with absolute time.
No, however, if they have the ability to get the current time, they obey constraints like these in a way a model a year ago didn't.
of you ask it, surely it can run a "time" in its sandbox from time to time and see how long it worked for
I wonder if the absolute value of the time result has any bearing on the subsequent analysis.
It is not necessarily the case that the instruction needs be taken literally
that can run date
The voice models certainly can't: https://kittygr.am/reel/DWr31A1B1Ux/
they can now https://www.youtube.com/watch?v=8vvWTz6N7Qg
> in just under one hour.
I wonder what the survivorship bias is though. How many other problems did they try but fail? Did they try to solve this problem but with another prompt? Still very impressive though.