We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human…
We trained "critique-writing" models to describe flaws in summaries. Human evaluators find flaws in summaries much more often when shown…
Large neural networks are at the core of many recent advances in AI, but training them is a difficult engineering…
Cohere, OpenAI, and AI21 Labs have developed a preliminary set of best practices applicable to any organization developing or deploying…
OpenAI Codex, a natural language-to-code system based on GPT-3, helps turn simple English instructions into over a dozen popular coding…
Last month, we started previewing DALL·E 2 to a limited number of trusted users to learn about the technology’s capabilities…
Greg Brockman is becoming President, a new role which reflects his unique combination of personal coding contributions on our critical…
Goodhart’s law famously says: “When a measure becomes a target, it ceases to be a good measure.” Although originally from…
by Ehtsham Elahiwith James McInerney, Nathan Kallus, Dario Garcia Garcia and Justin BasilicoIntroductionThis writeup is about using reinforcement learning to construct…
Virtual Production — A Validation Framework For Unreal EngineBy Adam Davis, Jimmy Fusil, Bhanu Srikanth and Girish BalakrishnanGame Engines in Virtual ProductionThe use…