工程 AI 探索

The challenges and decisions behind AI Discover’s intelligence layer

AI Discover 智能层背后的挑战与决策

By Varun Khaitan, Peng Ren, Gary Tang, Itay Teller, Atif Faheem, Nipun Kumar, Donnie DeBoer, Eduardo Lundgren, Matteo Rinaldi, Raghav Bakshi

作者:Varun Khaitan、Peng Ren、Gary Tang、Itay Teller、Atif Faheem、Nipun Kumar、Donnie DeBoer、Eduardo Lundgren、Matteo Rinaldi、Raghav Bakshi

We recently introduced AI Discover, a new tab in our TV app where a small group of members can try new ways to find something to watch. For years, our recommendations have worked in the background, inferring what a member might enjoy from their viewing history. AI Discover moves from that silent ranking toward steerable discovery. A member picks a theme, say “Quick Watches,” and gets a row of matching titles, a short note on why they fit and a few narrower themes to try next. From there, they can keep narrowing, head somewhere new or tune what they see.

我们最近推出了 AI Discover,这是电视应用中的一个新标签页,一小部分会员可以在这里尝试新的找片方式。多年来,我们的推荐一直在后台运作,根据会员的观看历史推断他们可能喜欢什么。AI Discover 从那种默默进行的排序转向可引导的发现。会员选择一个主题,比如“Quick Watches”,就会得到一排匹配的作品、一段说明它们为何契合的简短文字,以及几个更细分的主题供下一步尝试。从那里,他们可以继续缩小范围、转向新的方向,或调整所看到的内容。

Building AI Discover raised a question many teams will recognize: how do you deliver a better member experience with generative AI on TV without sacrificing speed, reliability or safety? Our answer is a new intelligence layer, the agent harness behind AI Discover. For each request, it decides how to combine LLMs with our recommendation systems. It builds on years of work understanding what members enjoy, and on our recent work applying LLMs to recommendations and generative experiences. The layer itself plans each request, runs it across those systems, serves the result and evaluates it offline.

构建 AI Discover 引发了一个许多团队都熟悉的问题:如何在不牺牲速度、可靠性或安全性的前提下,在电视上通过生成式 AI 提供更好的会员体验?我们的答案是新的智能层,也就是 AI Discover 背后的智能体执行框架。对于每个请求,它决定如何将大语言模型与我们的推荐系统结合起来。它建立在多年来理解会员喜好的工作之上,也建立在我们近期将大语言模型应用于推荐和生成式体验的工作之上。这个层本身会规划每个请求,在这些系统中运行它,提供结果,并在离线环境中对其进行评估。

This post covers the challenges we designed for and th...

开通本站会员,查看完整译文。

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.156.0. UTC+08:00, 2026-11-18 15:01
浙ICP备14020137号-1