Developer Resources
Ilan demos how to create human-level latency with the new Realtime API.
Noah builds evals with OpenAI o1 to boost performance.
# Technical Support & Enablement
Roy shares how to leverage o1, OpenAI's new series of reasoning models. Sourcegraph presents their production use case.
Anoop shares how to improve cost, latency, and performance with distillation.
Max dives into solutions for tailored customization.
Joe highlights best practices and common applications.
Shyamal shares model structures and eval best practices.
Ilan shares orchestration techniques to build multi-assistant systems.
Katia demos how to achieve 100% reliability with our new SO feature.
Noah fine-tunes our newest model, GPT-4o mini.