{"id":"0ff242e1-dc3f-4776-8b1a-b5d3992842d6","url":"https://api.tumn.com/news/0ff242e1-dc3f-4776-8b1a-b5d3992842d6","title":"Turning Opportunistic AI Inference Capacity Into Better Ads Recommendations","summary":"At Meta, we’ve built a system that enhances ads recommendations by leveraging idle inference capacity in our fleet. Two elasticity levers in the system allow ads recommendation work to expand across opportunistic capacity, without compromising baseline performance. This post desc","sections":[],"faq":[],"sources":[{"url":"https://engineering.fb.com/2026/10/12/ml-applications/turning-opportunistic-ai-inference-capacity-into-better-ads-recommendations/","title":"Meta Engineering","publishedAt":"2026-10-12T16:00:50.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-12T16:00:50.000Z","modifiedAt":"2026-10-12T20:24:46.000Z","checkedAt":"2026-10-12T20:24:46.477Z","language":"ko","kind":"link","sourceLabel":"AI 공식","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/0ff242e1-dc3f-4776-8b1a-b5d3992842d6.json","markdown":"https://api.tumn.com/news/0ff242e1-dc3f-4776-8b1a-b5d3992842d6.md"}}