<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
        xmlns:news="http://www.google.com/schemas/sitemap-news/0.9">
  <url>
    <loc>https://samtaelabs.com/blog/claude-api-token-cost-input-output-difference</loc>
    <news:news>
      <news:publication>
        <news:name>삼태연구소</news:name>
        <news:language>ko</news:language>
      </news:publication>
      <news:publication_date>2026-08-15T12:30:36.184Z</news:publication_date>
      <news:title>Claude API 토큰 비용의 진짜 구조: Input과 Output이 5배 차이 나는 이유</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://samtaelabs.com/blog/ai-design-agent-watermark-outsourcing-changes</loc>
    <news:news>
      <news:publication>
        <news:name>삼태연구소</news:name>
        <news:language>ko</news:language>
      </news:publication>
      <news:publication_date>2026-08-15T03:00:27.929Z</news:publication_date>
      <news:title>AI가 디자인하고, 일하고, 워터마크까지 찍는다 — 개발 외주 현장이 바뀌는 3가지 신호</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://samtaelabs.com/blog/ai-coding-tool-for-outsourcing-agency</loc>
    <news:news>
      <news:publication>
        <news:name>삼태연구소</news:name>
        <news:language>ko</news:language>
      </news:publication>
      <news:publication_date>2026-08-14T22:30:02.874Z</news:publication_date>
      <news:title>AI 코딩 도구, 개발 외주 업체는 어떻게 써야 하는가</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://samtaelabs.com/blog/glm-5-3-open-source-coding-model-50-percent-improvement</loc>
    <news:news>
      <news:publication>
        <news:name>삼태연구소</news:name>
        <news:language>ko</news:language>
      </news:publication>
      <news:publication_date>2026-08-14T12:30:36.064Z</news:publication_date>
      <news:title>GLM-5.3: 포스트 트레이닝만으로 코딩 성능 50% 끌어올린 오픈소스 모델</news:title>
    </news:news>
  </url>
</urlset>