Already made a harness for Claude to make R/W plans, not write once like they are usually implemented. They can modify themselves as they work through the task at hand. Also relying on a collection of patterns for writing coding task plans which evolves by reflection. Everything is designed so I could run Claude in yolo-mode in a sandbox for long stretches of time.
Already made a harness for Claude to make R/W plans, not write once like they are usually implemented. They can modify themselves as they work through the task at hand. Also relying on a collection of patterns for writing coding task plans which evolves by reflection. Everything is designed so I could run Claude in yolo-mode in a sandbox for long stretches of time.
Link?
As a VC in 2026 I'm going to be asking every company "but what's your harness strategy?"
Given that you're likely in San Francisco, make sure you say "AI Harness".
It’s all about user-specific bindings.
2027 is the year of the "maybe indeterminism isn't as valueable as we thought"
But will harness build desktop Linux for us?
Only if you put bells on it and sing Jingle Bells while it em dashes through the snow.
My harness is improving my Linux desktop...