Greg Brockman is becoming President, a new role which reflects his unique combination of personal coding contributions on our critical path together with company strategy. He is currently focused on training our flagship AI systems. Brad Lightcap has been pivotal in OpenAI’s growth, scaling our structure, team, and capital base through his oversight of our …
Goodhart’s law famously says: “When a measure becomes a target, it ceases to be a good measure.” Although originally from economics, it’s something we have to grapple with at OpenAI when figuring out how to optimize objectives that are difficult or costly to measure. It’s often necessary to introduce some proxy objective that’s easier or …
by Ehtsham Elahiwith James McInerney, Nathan Kallus, Dario Garcia Garcia and Justin Basilico Introduction This writeup is about using reinforcement learning to construct an optimal list of recommendations when the user has a finite time budget to make a decision from the list of recommendations. Working within the time budget introduces an extra resource constraint for …
Read more “Reinforcement Learning for Budget Constrained Recommendations”
Virtual Production — A Validation Framework For Unreal Engine By Adam Davis, Jimmy Fusil, Bhanu Srikanth and Girish Balakrishnan Game Engines in Virtual Production The use of Virtual Production and real time technologies has markedly accelerated in the past few years. At Netflix, we are always thrilled to see technology enable new ways of telling stories, and the …
Read more “Virtual Production — A Validation Framework For Unreal Engine”
Data Mesh — A Data Movement and Processing Platform @ Netflix By Bo Lei, Guilherme Pires, James Shao, Kasturi Chatterjee, Sujay Jain, Vlad Sydorenko Background Realtime processing technologies (A.K.A stream processing) is one of the key factors that enable Netflix to maintain its leading position in the competition of entertaining our users. Our previous generation of streaming pipeline …
Read more “Data Mesh — A Data Movement and Processing Platform @ Netflix”
by Aryan Mehrawith Farnaz Karimdady Sharifabad, Prasanna Vijayanathan, Chaïna Wade, Vishal Sharma and Mike Schassberger Aim and Purpose — Problem Statement The purpose of this article is to give insights into analyzing and predicting “out of memory” or OOM kills on the Netflix App. Unlike strong compute devices, TVs and set top boxes usually have stronger memory …
By Alex Hutter, Falguni Jhaveri, and Senthil Sayeebaba In a previous post, we described the indexing architecture of Studio Search and how we scaled the architecture by building a config-driven self-service platform that allowed teams in Content Engineering to spin up search indices easily. This post will discuss how Studio Search supports querying the data available …
Read more “How Netflix Content Engineering makes a federated graph searchable (Part 2)”
By Astha Singhal, Lakshmi Sudheer, Julia Knecht The Application Security teams at Netflix are responsible for securing the software footprint that we create to run the Netflix product, the Netflix studio, and the business. Our customers are product and engineering teams at Netflix that build these software services and platforms. The Netflix cultural values of ‘Context …
At Netflix, we want to entertain the world through creating engaging content and helping members discover the titles they will love. Key to that is understanding causal effects that connect changes we make in the product to indicators of member joy. To measure causal effects we rely heavily on AB testing, but we also leverage quasi-experimentation …
Read more “A Survey of Causal Inference Applications at Netflix”
by Vivek Kaushal At Netflix, we aim to provide recommendations that match our members’ interests. To achieve this, we rely on Machine Learning (ML) algorithms. ML algorithms can be only as good as the data that we provide to it. This post will focus on the large volume of high-quality data stored in Axion — our fact store …