Model Routing 도입을 통한 LLM 운영 비용 80% 절감
Cutting our LLM bill ~80% with model routing: the actual cost math
Cutting our LLM bill ~80% with model routing: the actual cost math
Most AI projects fail in production. It's rarely the model.
I Built a 131-Test Eval Harness Before Writing New Features. Here's the Silent Failure It Caught.
How to Fine-Tune LLMs on Your Own Data: Open-Source Models, RL Environments, and Evals
Why We're Changing Our Default Eval Model
What I learned building a tiny PR-review bot in 10 days
AI 에이전트 시대의 가치 측정: 단순 인게이지먼트에서 품질 중심 지표로의 전환
I've Shipped 113 Local-AI Projects in 18 Months — Here Are the Five Architecture Patterns That Actually Survived