OpenAIReinforcement learning with prediction-based rewards
Exploring the integration of reinforcement learning with prediction-based rewards.
OpenAILearning complex goals with iterated amplification
Maximizing goal achievement through iterated amplification methods
OpenAIOpenAI Scholars 2019: Applications open
A guide to applying for the OpenAI Scholars 2019 program
OpenAIOpenAI Fellows Winter 2019 & Interns Summer 2019
Insights and Updates on OpenAI Fellows and Interns Programs
OpenAIFFJORD: Free-form continuous dynamics for scalable reversible generative models
Exploring FFJORD for scalable reversible generative models
Jane StreetHow to shuffle a big dataset
Addressing the engineering challenge of shuffling a large dataset with a low signal-to-noise ratio.
Jane StreetDeep learning experiments in OCaml
Reproducing classical deep learning results in OCaml using TensorFlow and training models defined in a functional way on a GPU.
SoundCloudUsing Kubernetes Pod Metadata to Improve Zipkin Traces
Leveraging Kubernetes pod metadata to normalize Zipkin service names and enrich trace spans, enabling faster latency debugging across hundreds of microservices.
SoundCloudUsing Kubernetes Pod Metadata to Improve Zipkin Traces
Practical guide to enriching Zipkin traces by leveraging Kubernetes pod metadata to normalize service names and attach rich annotations for faster, more accurate latency debugging across microservices.
SoundCloudUsing Kubernetes Pod Metadata to Improve Zipkin Traces
Improving Zipkin traces by utilizing Kubernetes Pod Metadata for debugging latency issues across microservices
OpenAIOpenAI Scholars 2018: Final projects
Exploring innovative final projects from OpenAI Scholars 2018 cohort.
SoundCloudHands-Off Deployment with Canary
Hands-Off Deployment with Canary illustrates evolving from manual canary testing to an automated CD pipeline with canary releases, automated verification, and monitoring to safely roll back faulty deployments and reduce MTTR.