Atlarix 하네스를 통한 open-weight 모델의 성능 병목 제거 확인 (정확도 47%)
Atlarix vs opencode on Terminal-Bench 2.0 — same model, only the harness changes (k=1, receipts included)
Atlarix vs opencode on Terminal-Bench 2.0 — same model, only the harness changes (k=1, receipts included)
The Harness Is Now the Product
The AI agent loop, in ~150 lines (no framework)
"My AI Assistant Could Code, But It Couldn't Operate My Desktop"
Checkbox theater: how I stopped trusting my AI agent to run the checks
AI Agents in Practice — Part 2: What Makes Something an Agent
Agent Loop and Harness: A Practical Engineering View of AI Operations
Kubernetes, Finally Explained
🤖 What is an AI Agent? A Beginner's Guide to the Future of AI
Closed-Loop FinOps: Detect, Decide, Act, Verify in 5 Minutes
Discord Integration Pattern for Alerts and Control Loops
Can Claude Fly a Plane?
Asynchronous Robot Inference: Decoupling Action Prediction and Execution