Own the continuity, not the whole stack
Busy39 tried to own too much of the runtime. Studying a smaller orchestration system clarified the next goal: own the continuity.
Lynn Cole / Writing
Essays, thoughts, and technical notes.
Busy39 tried to own too much of the runtime. Studying a smaller orchestration system clarified the next goal: own the continuity.
A statistical lead-generation system, an unchecked SQL error, and a cron typo that turned a promising experiment into an inbox fire.
My coding agent is arguing with its ticket system. Persistent roles and procedural memory create unexpected standards—and a useful kind of bureaucracy.
A long-horizon solver is not finished when it runs for hours. The real benchmark is generalizing coherent work, recovery and handoffs across different models.
After OpenClaw, the harder problem is continuity across hours, days and weeks. The opportunity is to let people bring their agents to better tools.
Context shaping is more than delegation: iteration, problem solving, manual rewrites and interfaces designed around people.
I want digital painting to feel less sanitary: a canvas driven by hand movements, voice commands and a game engine, where the colors can finally get their hands dirty.
Build tools for the inference stack people already use: delightful software, a community and something worth returning to.
Every time I bring up Fortran in a discussion with engineers who don’t specialize in it, someone always wants to talk about COBOL.
A correct theorem about a narrow multi-agent abstraction does not settle the value of systems with persistent state, tools and fresh environmental feedback.
Copying an existing agent harness can be fast. Discovering and handling its real failure modes is where the engineering time goes.
Meta-harnesses are self-customizing software. I have been building them since my first LLM agent project and want to share where the difficult pieces live.