faang

Learning to Play Minecraft with Video PreTraining (VPT)

We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human…

3 years ago

AI-Written Critiques Help Humans Notice Flaws

We trained "critique-writing" models to describe flaws in summaries. Human evaluators find flaws in summaries much more often when shown…

3 years ago

Techniques for Training Large Neural Networks

Large neural networks are at the core of many recent advances in AI, but training them is a difficult engineering…

3 years ago

Best Practices for Deploying Language Models

Cohere, OpenAI, and AI21 Labs have developed a preliminary set of best practices applicable to any organization developing or deploying…

3 years ago

Powering Next Generation Applications with OpenAI Codex

OpenAI Codex, a natural language-to-code system based on GPT-3, helps turn simple English instructions into over a dozen popular coding…

3 years ago

DALL·E 2 Research Preview Update

Last month, we started previewing DALL·E 2 to a limited number of trusted users to learn about the technology’s capabilities…

3 years ago

OpenAI Leadership Team Update

Greg Brockman is becoming President, a new role which reflects his unique combination of personal coding contributions on our critical…

3 years ago

Measuring Goodhart’s Law

Goodhart’s law famously says: “When a measure becomes a target, it ceases to be a good measure.” Although originally from…

3 years ago

Reinforcement Learning for Budget Constrained Recommendations

by Ehtsham Elahiwith James McInerney, Nathan Kallus, Dario Garcia Garcia and Justin BasilicoIntroductionThis writeup is about using reinforcement learning to construct…

3 years ago

Virtual Production — A Validation Framework For Unreal Engine

Virtual Production — A Validation Framework For Unreal EngineBy Adam Davis, Jimmy Fusil, Bhanu Srikanth and Girish BalakrishnanGame Engines in Virtual ProductionThe use…

3 years ago