Commentary

The following originally appeared on Hugo Bowne-Anderson’s Vanishing Gradients Substack and is being republished here with the author’s permission. The conversation around harness engineering is dominated by problems from coding and personal agents such as OpenClaw, but most agents are simpler. Builders should avoid over-engineering for capabilities that newer models may absorb anyway, the “Kirby […]

I’ve been working on the Quality Playbook, my open source AI skill that uses quality engineering to find bugs that normal AI code review misses, and I recently had a batch of work that turned into a long run of point releases. I was using Claude Cowork as the orchestrator: planning scope, dispatching instructions to

Somewhere in a Singapore data center, a bank is paying for eight H100s that spend most of the night waiting. The cluster was bought for good reasons (discomfort with customer documents leaving the building, a strategy team’s aversion to lock-in), so the bank secured its own sovereign compute. Now the finance team is asking why

I keep seeing the same idea in conversations about agents: detailed specs are old-world overhead now. Give the model a rough goal, let it explore, fix what comes back, move on. It sounds efficient but it also hides the cost. A simple prompt looks cheap and tempting because it gets implementation started right away. Then

My job is developer productivity. I’ve worked in developer infrastructure for six years now so I have skin in the game here. I want the AI productivity story to be true. More output, tighter timelines, happier and more productive engineers. Who wouldn’t? But I keep looking at the actual research and then looking at what’s

Autonomous agents are moving faster than the field’s ability to govern them, and catching up requires more than better prompts or bigger sandboxes. At O’Reilly’s recent AI Superstream focused on OpenClaw and the broader ecosystem of locally run and self-hosted AI agents, five speakers, each working at a different layer of the stack, explored patterns

Autonomous agents are moving faster than the field’s ability to govern them, and catching up requires more than better prompts or bigger sandboxes. At O’Reilly’s recent AI Superstream focused on OpenClaw and the broader ecosystem of locally run and self-hosted AI agents, five speakers, each working at a different layer of the stack, explored patterns

The following article originally appeared on Paolo Perrone’s Substack, The AI Engineer, and is being republished here with the author’s permission. You spent three weeks shipping an agent. It worked in the demo. Then production hit, and you realized the framework you picked has no checkpointing, the memory layer is a flat vector dump with

AI-assisted development has made frontend work feel much faster. A developer can ask for a form, a dashboard card, a table, a modal, or a responsive layout and get a decent first version almost immediately. The code may compile. The page may render. At first glance, the UI may look done. But frontend developers know