A personal experiment to help AI agents understand time
A l experiment is adding a dedicated time feature to an to help with weak time awareness. The goal is to make the agent copy parts of how people sense time, plan, and keep while doing tasks.
This feature is designed like a time-processing organ called “Unruh.” Because an LLM may miss the practical meaning of raw dates and , Unruh turns saved schedule data into easier relative wording before putting it into the . For example, a dinner saved as “Dinner with Mom 07082026T18:00:00” becomes wording like “Dinner with Mom on Wednesday, July 8, 6pm,” plus “Wednesday next week” and “three days ahead.” Some parts of the system already work fairly well.
Key points
- The experiment adds a separate time-processing feature to an .
- Dates are stored in a fixed timestamp-like form, then rewritten into plain relative wording.
- The agent receives details like “next week” and “three days ahead,” not only the calendar date.
- The aim is to improve planning, priority, and task .
- This may increase tokens per prompt, but could reduce wasted agent steps.