miniblog.

After further playing with my LLM project, I'm surprised how hard it is to tune with system prompts. My agent kept saying "obviously" even though my prompt said "helpful, professional". Eventually I found that a "courteous" prompt gets "of course" which is better but not ideal.

I certainly see the appeal of an LLM system with full context and tool use (OpenClaw), but the lethal trifecta puts me off deploying it. I do like the idea of an agent with a heartbeat though. A bunch of nice cron-style workflows can be built on top.

A cute systemd feature to get the system clock roughly correct: if the system time is before the compilation time of the systemd binary, it moves the clock forward to that time!