We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human Minecraft play, while using only a small amount of labeled contractor data. With fine-tuning, our model can learn to craft diamond tools, a task that usually takes proficient humans over 20 minutes (24,000 actions). Our …
Read more “Learning to Play Minecraft with Video PreTraining (VPT)”
We trained “critique-writing” models to describe flaws in summaries. Human evaluators find flaws in summaries much more often when shown our model’s critiques. Larger models are better at self-critiquing, with scale improving critique-writing more than summary-writing. This shows promise for using AI systems to assist human supervision of AI systems on difficult tasks. Read paperView …
Large neural networks are at the core of many recent advances in AI, but training them is a difficult engineering and research challenge which requires orchestrating a cluster of GPUs to perform a single synchronized calculation. As cluster and model sizes have grown, machine learning practitioners have developed an increasing variety of techniques to parallelize …
Cohere, OpenAI, and AI21 Labs have developed a preliminary set of best practices applicable to any organization developing or deploying large language models. Computers that can read and write are here, and they have the potential to fundamentally impact daily life. The future of human–machine interaction is full of possibility and promise, but any powerful …
OpenAI Codex, a natural language-to-code system based on GPT-3, helps turn simple English instructions into over a dozen popular coding languages. Codex was released last August through our API and is the principal building block of GitHub Copilot. Our motivation behind Codex is to supplement developers’ work and increase productivity. Codex helps computers to better …
Read more “Powering Next Generation Applications with OpenAI Codex”
Last month, we started previewing DALL·E 2 to a limited number of trusted users to learn about the technology’s capabilities and limitations. Since then, we’ve been working with our users to actively incorporate the lessons we learn. As of today: Our users have collectively created over 3 million images with DALL·E. We’ve enhanced our safety …
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”