A shared inference broker for local agents
One of the more interesting problems I’m working through in my coding agent app is scheduling.
Lynn Cole / Writing
Writing
Essays, thoughts, and technical notes.
Token consumption is not productivity
Inference volume can rise because useful work is happening—or because a project is falling apart.
The old religion of Python
Python once felt like a doctrine of disciplined predictability. An architectural failure got me thinking about explicit contracts and where rigidity belongs.
We have had the vibe-coding argument before
We have heard the vibe-coding argument before—in digital art, visual programming, web design, music and animation. Lowering the barrier changes who gets to try.
Agentic browsing and protected browser state
Agentic browsing should preserve the browser’s security boundaries. Extracting passwords, cookies and session state into model context changes the whole risk.
Engineering the conditions for automated work
The velocity AI creates in coding is interesting because it is not nearly as uniform as people assume.
Remembering CodeCharge’s global and local views
CodeCharge’s global, layout and data views made a memorable model for generating applications. I miss that way of seeing the work.
When old documentation starts steering new agents
Documentation becomes an instruction surface when agents read it. Borrowing old code can accidentally bring an obsolete architecture back to life.
Idle workers: automation that yields to humans
Idle workers perform tasks while a device is unused, yield when the human returns, and resume where they left off.
Ends, Means, and AI: The System Design Principle We’re Overlooking
Thinking about ends, means, subjects and objects changes how you design agentic systems. State and continuity define an architectural boundary worth guarding.
Personas, repository instructions, and alignment
Personas can encode beliefs and boundaries without turning repository instructions into a tax code. Instruction mass changes how agents work.
What commit insertions and deletions might tell you
Commit insertions and deletions can reveal churn, unfinished work or oversized commits. I look for patterns rather than treating volume as achievement.