<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title><![CDATA[OpenAI Engineering News]]></title>
        <description><![CDATA[The OpenAI engineering blog]]></description>
        <link>https://openai.com/news/engineering</link>
        <generator>OpenAI</generator>
        <lastBuildDate>Mon, 26 Oct 2026 10:34:17 GMT</lastBuildDate>
        <atom:link href="https://openai.com/news/engineering/rss.xml" rel="self" type="application/rss+xml"/>
        <language><![CDATA[en-US]]></language>
        <item>
            <title><![CDATA[Rapidly scaling online storage to serve over 1 billion ChatGPT users (Part II)]]></title>
            <description><![CDATA[Learn how OpenAI scaled Habitat with reliable multi-tenancy, global caching, and Azure Cosmos DB to deliver 12× faster reads for ChatGPT.]]></description>
            <link>https://openai.com/index/scaling-storage-one-billion-users-part-two</link>
            <guid isPermaLink="true">https://openai.com/index/scaling-storage-one-billion-users-part-two</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Fri, 23 Oct 2026 17:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How we built ChatGPT’s novel ad stack for user trust and relevance]]></title>
            <description><![CDATA[Learn how OpenAI built ChatGPT’s LLM-powered ad stack to understand conversational intent, keep ads separate from answers, and deliver relevant ads at scale.]]></description>
            <link>https://openai.com/index/building-chatgpt-ad-stack</link>
            <guid isPermaLink="true">https://openai.com/index/building-chatgpt-ad-stack</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Wed, 21 Oct 2026 07:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Rapidly scaling online storage to serve over 1 billion ChatGPT users]]></title>
            <description><![CDATA[Learn how OpenAI evolved Habitat from a Python library into a globally distributed storage platform serving 1 billion ChatGPT users and 22M requests per second.]]></description>
            <link>https://openai.com/index/scaling-storage-one-billion-users-part-one</link>
            <guid isPermaLink="true">https://openai.com/index/scaling-storage-one-billion-users-part-one</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Fri, 11 Sep 2026 10:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Jalapeño’s first results show industry-leading speed and efficiency in AI inference]]></title>
            <description><![CDATA[Jalapeño is a custom inference chip from OpenAI that delivers faster, more power-efficient AI inference, with higher throughput and lower latency for modern models.]]></description>
            <link>https://openai.com/index/jalapeno-first-results</link>
            <guid isPermaLink="true">https://openai.com/index/jalapeno-first-results</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Tue, 25 Aug 2026 07:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How we built a realtime system for responsive voice AI in six months]]></title>
            <description><![CDATA[GPT-Live enables continuous voice interaction with AI, using a turnless speech model and low-latency architecture for faster, more natural conversations.]]></description>
            <link>https://openai.com/index/continuous-voice-interaction-with-gpt-live</link>
            <guid isPermaLink="true">https://openai.com/index/continuous-voice-interaction-with-gpt-live</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Mon, 03 Aug 2026 07:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How GPT-5.6 fuses frontier intelligence with frontier efficiency]]></title>
            <description><![CDATA[GPT-5.6 improves AI efficiency across models, inference, and agentic workflows, helping deliver more useful intelligence per dollar.]]></description>
            <link>https://openai.com/index/gpt-5-6-frontier-intelligence-efficiency</link>
            <guid isPermaLink="true">https://openai.com/index/gpt-5-6-frontier-intelligence-efficiency</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Wed, 29 Jul 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Core dump epidemiology: fixing an 18-year-old bug]]></title>
            <description><![CDATA[OpenAI engineers used large-scale core dump analysis to debug rare infrastructure crashes, uncovering both a hardware fault and a long-standing software bug.]]></description>
            <link>https://openai.com/index/core-dump-epidemiology-data-infrastructure-bug</link>
            <guid isPermaLink="true">https://openai.com/index/core-dump-epidemiology-data-infrastructure-bug</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Tue, 30 Jun 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Building self-improving tax agents with Codex]]></title>
            <description><![CDATA[See how OpenAI, Thrive, and Crete built a self-improving tax agent with Codex, automating filings, improving accuracy, and accelerating workflows.]]></description>
            <link>https://openai.com/index/building-self-improving-tax-agents-with-codex</link>
            <guid isPermaLink="true">https://openai.com/index/building-self-improving-tax-agents-with-codex</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Wed, 27 May 2026 07:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Building a safe, effective sandbox to enable Codex on Windows]]></title>
            <description><![CDATA[Learn how OpenAI built a safe, effective sandbox to enable Codex on Windows with controlled file access and network limits.]]></description>
            <link>https://openai.com/index/building-codex-windows-sandbox</link>
            <guid isPermaLink="true">https://openai.com/index/building-codex-windows-sandbox</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Wed, 13 May 2026 11:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Unlocking large scale AI training networks with MRC (Multipath Reliable Connection)]]></title>
            <description><![CDATA[OpenAI introduces MRC (Multipath Reliable Connection), a new supercomputer networking protocol released via OCP to improve resilience and performance in large-scale AI training clusters.]]></description>
            <link>https://openai.com/index/mrc-supercomputer-networking</link>
            <guid isPermaLink="true">https://openai.com/index/mrc-supercomputer-networking</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Tue, 05 May 2026 10:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How OpenAI delivers low-latency voice AI at scale]]></title>
            <description><![CDATA[How OpenAI rebuilt its WebRTC stack to power real-time Voice AI with low latency, global scale, and seamless conversational turn-taking.]]></description>
            <link>https://openai.com/index/delivering-low-latency-voice-ai-at-scale</link>
            <guid isPermaLink="true">https://openai.com/index/delivering-low-latency-voice-ai-at-scale</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Mon, 04 May 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[An open-source spec for orchestration: Symphony]]></title>
            <description><![CDATA[Learn how Symphony, an open-source spec for Codex orchestration, turns issue trackers into always-on agent systems—boosting engineering output and reducing context switching.]]></description>
            <link>https://openai.com/index/open-source-codex-orchestration-symphony</link>
            <guid isPermaLink="true">https://openai.com/index/open-source-codex-orchestration-symphony</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Mon, 27 Apr 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Speeding up agentic workflows with WebSockets in the Responses API]]></title>
            <description><![CDATA[A deep dive into the Codex agent loop, showing how WebSockets and connection-scoped caching reduced API overhead and improved model latency.]]></description>
            <link>https://openai.com/index/speeding-up-agentic-workflows-with-websockets</link>
            <guid isPermaLink="true">https://openai.com/index/speeding-up-agentic-workflows-with-websockets</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Wed, 22 Apr 2026 10:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[From model to agent: Equipping the Responses API with a computer environment ]]></title>
            <description><![CDATA[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.]]></description>
            <link>https://openai.com/index/equip-responses-api-computer-environment</link>
            <guid isPermaLink="true">https://openai.com/index/equip-responses-api-computer-environment</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Wed, 11 Mar 2026 11:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Beyond rate limits: scaling access to Codex and Sora]]></title>
            <description><![CDATA[How OpenAI built a real-time access system combining rate limits, usage tracking, and credits to power continuous access to Sora and Codex.]]></description>
            <link>https://openai.com/index/beyond-rate-limits</link>
            <guid isPermaLink="true">https://openai.com/index/beyond-rate-limits</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Fri, 13 Feb 2026 09:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Harness engineering: leveraging Codex in an agent-first world]]></title>
            <description><![CDATA[By Ryan Lopopolo, Member of the Technical Staff]]></description>
            <link>https://openai.com/index/harness-engineering</link>
            <guid isPermaLink="true">https://openai.com/index/harness-engineering</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Wed, 11 Feb 2026 09:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Unlocking the Codex harness: how we built the App Server]]></title>
            <description><![CDATA[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.]]></description>
            <link>https://openai.com/index/unlocking-the-codex-harness</link>
            <guid isPermaLink="true">https://openai.com/index/unlocking-the-codex-harness</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Wed, 04 Feb 2026 13:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Inside OpenAI’s in-house data agent]]></title>
            <description><![CDATA[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.]]></description>
            <link>https://openai.com/index/inside-our-in-house-data-agent</link>
            <guid isPermaLink="true">https://openai.com/index/inside-our-in-house-data-agent</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Thu, 29 Jan 2026 10:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Unrolling the Codex agent loop]]></title>
            <description><![CDATA[A technical deep dive into the Codex agent loop, explaining how Codex CLI orchestrates models, tools, prompts, and performance using the Responses API.]]></description>
            <link>https://openai.com/index/unrolling-the-codex-agent-loop</link>
            <guid isPermaLink="true">https://openai.com/index/unrolling-the-codex-agent-loop</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Fri, 23 Jan 2026 12:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Scaling PostgreSQL to power 800 million ChatGPT users]]></title>
            <description><![CDATA[An inside look at how OpenAI scaled PostgreSQL to millions of queries per second using replicas, caching, rate limiting, and workload isolation.]]></description>
            <link>https://openai.com/index/scaling-postgresql</link>
            <guid isPermaLink="true">https://openai.com/index/scaling-postgresql</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Thu, 22 Jan 2026 12:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How We Used Codex to Ship Sora for Android in 28 Days]]></title>
            <description><![CDATA[OpenAI shipped Sora for Android in 28 days using Codex. AI-assisted planning, translation, and parallel coding workflows helped a nimble team deliver rapid, reliable development.]]></description>
            <link>https://openai.com/index/shipping-sora-for-android-with-codex</link>
            <guid isPermaLink="true">https://openai.com/index/shipping-sora-for-android-with-codex</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Fri, 12 Dec 2025 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How we built OWL, the new architecture behind our ChatGPT-based browser, Atlas]]></title>
            <description><![CDATA[A deep dive into OWL, the new architecture powering ChatGPT Atlas—decoupling Chromium, enabling fast startup, rich UI, and agentic browsing with ChatGPT.]]></description>
            <link>https://openai.com/index/building-chatgpt-atlas</link>
            <guid isPermaLink="true">https://openai.com/index/building-chatgpt-atlas</guid>
            <category><![CDATA[Engineering]]></category>
            <pubDate>Thu, 30 Oct 2025 00:00:00 GMT</pubDate>
        </item>
    </channel>
</rss>