LLM Skill-set의 정량적 측정 및 자동 최적화 루프 구현
oh-my-agent: skills now measure and optimize their own utility
oh-my-agent: skills now measure and optimize their own utility
Agentic AI in software development: what's actually production-ready in 2026
Opus 4.7 기반 SWE-bench 87% 달성 및 Cloud Agent 자율성 극대화
I added a local eval loop to my personal AI assistant — here's what 800 scored interactions taught me