OpenAI Engineering News
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
- Posts
- 26 from 30 Oct 2025 to 23 Oct 2026
- Posting
- weekly (25 in the last year)
- Kind
- company blog
- Feed
- https://openai.com/news/engineering/rss.xml
2026 24
- Rapidly scaling online storage to serve over 1 billion ChatGPT users (Part II)
- How we built ChatGPT’s novel ad stack for user trust and relevance
- GPT-6 Astra
- Rapidly scaling online storage to serve over 1 billion ChatGPT users
- Jalapeño’s first results show industry-leading speed and efficiency in AI inference
- GPT-6.1 Sol
- How we built a realtime system for responsive voice AI in six months
- How GPT-5.6 fuses frontier intelligence with frontier efficiency
- GPT-5.6
- Core dump epidemiology: fixing an 18-year-old bug
- Building self-improving tax agents with Codex
- Building a safe, effective sandbox to enable Codex on Windows
- Unlocking large scale AI training networks with MRC (Multipath Reliable Connection)
- How OpenAI delivers low-latency voice AI at scale
- An open-source spec for orchestration: Symphony
- GPT-5.5
- Speeding up agentic workflows with WebSockets in the Responses API
- From model to agent: Equipping the Responses API with a computer environment
- Beyond rate limits: scaling access to Codex and Sora
- Harness engineering: leveraging Codex in an agent-first world
- Unlocking the Codex harness: how we built the App Server
- Inside OpenAI’s in-house data agent
- Unrolling the Codex agent loop
- Scaling PostgreSQL to power 800 million ChatGPT users