Engineering
18 posts
How we built a realtime system for responsive voice AI in six months
GPT-Live enables continuous voice interaction with AI, using a turnless speech model and low-latency architecture for faster, more natural conversations.
How GPT-5.6 fuses frontier intelligence with frontier efficiency
GPT-5.6 improves AI efficiency across models, inference, and agentic workflows, helping deliver more useful intelligence per dollar.
Core dump epidemiology: fixing an 18-year-old bug
OpenAI engineers used large-scale core dump analysis to debug rare infrastructure crashes, uncovering both a hardware fault and a long-standing software bug.
Building self-improving tax agents with Codex
See how OpenAI, Thrive, and Crete built a self-improving tax agent with Codex, automating filings, improving accuracy, and accelerating workflows.
Building a safe, effective sandbox to enable Codex on Windows
Learn how OpenAI built a safe, effective sandbox to enable Codex on Windows with controlled file access and network limits.
Unlocking large scale AI training networks with MRC (Multipath Reliable Connection)
OpenAI introduces MRC (Multipath Reliable Connection), a new supercomputer networking protocol released via OCP to improve resilience and performance in larg…
How OpenAI delivers low-latency voice AI at scale
How OpenAI rebuilt its WebRTC stack to power real-time Voice AI with low latency, global scale, and seamless conversational turn-taking.
An open-source spec for orchestration: Symphony
Learn how Symphony, an open-source spec for Codex orchestration, turns issue trackers into always-on agent systems—boosting engineering output and reducing c…
Speeding up agentic workflows with WebSockets in the Responses API
A deep dive into the Codex agent loop, showing how WebSockets and connection-scoped caching reduced API overhead and improved model latency.
From model to agent: Equipping the Responses API with a computer environment
How OpenAI built an agent runtime using the Responses API, shell tool, and hosted containers to run secure, scalable agents with files, tools, and state.
Beyond rate limits: scaling access to Codex and Sora
How OpenAI built a real-time access system combining rate limits, usage tracking, and credits to power continuous access to Sora and Codex.
Harness engineering: leveraging Codex in an agent-first world
By Ryan Lopopolo, Member of the Technical Staff
Unlocking the Codex harness: how we built the App Server
Learn how to embed the Codex agent using the Codex App Server, a bidirectional JSON-RPC API powering streaming progress, tool use, approvals, and diffs.
Inside OpenAI’s in-house data agent
How OpenAI built an in-house AI data agent that uses GPT-5, Codex, and memory to reason over massive datasets and deliver reliable insights in minutes.
Unrolling the Codex agent loop
A technical deep dive into the Codex agent loop, explaining how Codex CLI orchestrates models, tools, prompts, and performance using the Responses API.
Scaling PostgreSQL to power 800 million ChatGPT users
An inside look at how OpenAI scaled PostgreSQL to millions of queries per second using replicas, caching, rate limiting, and workload isolation.
How We Used Codex to Ship Sora for Android in 28 Days
OpenAI shipped Sora for Android in 28 days using Codex. AI-assisted planning, translation, and parallel coding workflows helped a nimble team deliver rapid, …
How we built OWL, the new architecture behind our ChatGPT-based browser, Atlas
A deep dive into OWL, the new architecture powering ChatGPT Atlas—decoupling Chromium, enabling fast startup, rich UI, and agentic browsing with ChatGPT.
