Treat the coding-agent harness like a game engine: durable state, tools, configuration, the TUI, and inference become familiar engineering problems.

Harnesses get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be farther from the truth. The same model weights that score 30% on ARC-AGI score 95% with a better harness.

So we gathered a group of researchers…

What comes to mind when you hear "frontend optimization"? For most of us it's things like reducing network requests, shrinking the bundle,…

Carrying on in the face of creative devaluation.

on proving yourself, burning out, and being a good teammate