<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Codex on Yongjie Xue</title><link>https://www.yongjiexue.io/en/tags/codex/</link><description>Recent content in Codex on Yongjie Xue</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Mon, 07 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.yongjiexue.io/en/tags/codex/index.xml" rel="self" type="application/rss+xml"/><item><title>How Do You Burn Through 10 $200 Codex Subscriptions?</title><link>https://www.yongjiexue.io/en/ai/10x-subscription/</link><pubDate>Mon, 07 Sep 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/10x-subscription/</guid><description>Buying 10 AI subscriptions is easy. The real bottleneck is turning tokens into useful output—and using automation to scale your time, attention, and ability to judge the results.</description></item><item><title>GPT Astra Launch Giveaway: Free Banked Resets</title><link>https://www.yongjiexue.io/en/ai/astra-reset/</link><pubDate>Fri, 04 Sep 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/astra-reset/</guid><description>As Astra began rolling out, Tibo announced one banked reset per day for paid users still waiting for access. I&amp;rsquo;m stocking up for when Astra arrives.</description></item><item><title>OINK: After Six Years of Wrestling with Documentation Frameworks, Codex Finally Got Me Over the Line</title><link>https://www.yongjiexue.io/en/db/oink-release/</link><pubDate>Mon, 10 Aug 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/db/oink-release/</guid><description>After six years of trying eight approaches, I used Codex to combine Docsy&amp;rsquo;s engineering depth, Fumadocs&amp;rsquo; modern UX, and Hugo&amp;rsquo;s simple delivery model into OINK.</description></item><item><title>The Codex Reset Party Is Over. No More Free Eggs.</title><link>https://www.yongjiexue.io/en/ai/codex-reset-end/</link><pubDate>Sat, 08 Aug 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/codex-reset-end/</guid><description>OpenAI&amp;rsquo;s Codex Reset spree is over. The free eggs are gone—but what did one month with seven AI subscriptions, three computers, and two AGI-class models actually produce?</description></item><item><title>Quota Reset: Round N of the Codex/Claude War Begins</title><link>https://www.yongjiexue.io/en/ai/reset-codex-claude/</link><pubDate>Mon, 13 Jul 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/reset-codex-claude/</guid><description>Codex reset its quotas again this morning and dropped the five-hour limit. Claude immediately extended Fable access through the 17th. When vendors fight, users win—don&amp;rsquo;t miss the window.</description></item><item><title>Pedaling the Codex/Claude Bike Until the Wheels Smoke</title><link>https://www.yongjiexue.io/en/ai/bicycle/</link><pubDate>Fri, 10 Jul 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/bicycle/</guid><description>Claude Fable and GPT-5.6 have arrived back to back, followed by repeated quota resets. How do you turn a fleeting Coding Plan windfall into real output? Here is my playbook for model specialization, adversarial review, spec-driven design, closed-loop verification, context management, and one person leading a crew of AIs.</description></item><item><title>The Coding Plan Window Is Closing—Use It While It Lasts</title><link>https://www.yongjiexue.io/en/ai/coding-plan/</link><pubDate>Tue, 30 Jun 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/coding-plan/</guid><description>Coding Plans remain one of the best opportunities in the AI era: a subscription can unlock compute worth many times its price, but that window is already narrowing.</description></item><item><title>Cancel Claude, Switch to Codex</title><link>https://www.yongjiexue.io/en/ai/move-to-codex/</link><pubDate>Fri, 08 May 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/move-to-codex/</guid><description>When my $200 Claude Code Max subscription expired, I canceled it and moved my primary workflow to Codex. The only way to know which one is better is to put it to work.</description></item><item><title>A Busy Few Days in Infrastructure and AI</title><link>https://www.yongjiexue.io/en/ai/new-stuff/</link><pubDate>Thu, 23 Apr 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/new-stuff/</guid><description>Ubuntu 26.04 LTS, Qwen3.6-27B, ChatGPT Images 2.0, Privacy Filter, Anthropic Mythos, and the Claude Pro controversy all landed in quick succession. Here are the infrastructure and AI developments worth watching.</description></item><item><title>AI Survival Guide: Where the Biggest Arbitrage Really Is</title><link>https://www.yongjiexue.io/en/ai/ai-bonus/</link><pubDate>Tue, 10 Mar 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/ai-bonus/</guid><description>The biggest AI arbitrage available to ordinary users is not some obscure token play. It is the heavily subsidized max-tier subscription plans from frontier model vendors, provided you can convert that quota into real output.</description></item><item><title>OpenClaw Hype: Foam on Top of the Productivity Revolution</title><link>https://www.yongjiexue.io/en/ai/openclaw-hype/</link><pubDate>Mon, 09 Mar 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/openclaw-hype/</guid><description>OpenClaw looks exciting because it turns agents into a chat-style experience. But the real productivity gains come from high-capability subscription agents and disciplined workflows, not from lobster-flavored wrappers.</description></item><item><title>How Much Can One Person Get Done with AI over Spring Festival?</title><link>https://www.yongjiexue.io/en/ai/how-much-ai-can-do/</link><pubDate>Tue, 24 Feb 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/how-much-ai-can-do/</guid><description>Over roughly ten days during Spring Festival, I used Claude Code, Codex, and a pile of workflows to translate books, ship releases, package software, refresh websites, and keep publishing daily. This is what solo output looks like when agent leverage really lands.</description></item><item><title>When Coding Becomes Cheap, What Still Matters?</title><link>https://www.yongjiexue.io/en/ai/try-codex/</link><pubDate>Tue, 10 Feb 2026 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/ai/try-codex/</guid><description>Codex 5.3 xHigh pushed my workflow past a tipping point: writing code is no longer the scarce resource. The real leverage is design quality and engineering acceptance. This is the practical loop I use to ship reliable software with AI agents.</description></item><item><title>Scaling Postgres to the next level at OpenAI</title><link>https://www.yongjiexue.io/en/db/openai-pg/</link><pubDate>Mon, 19 May 2025 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/db/openai-pg/</guid><description>At PGConf.Dev 2025, Bohan Zhang from OpenAI shared a session titled Scaling Postgres to the next level at OpenAI, giving us a peek into the database usage of a top-tier unicorn.</description></item><item><title>OpenAI Global Outage Postmortem: K8S Circular Dependencies</title><link>https://www.yongjiexue.io/en/cloud/openai-failure/</link><pubDate>Sat, 14 Dec 2024 00:00:00 +0000</pubDate><guid>https://www.yongjiexue.io/en/cloud/openai-failure/</guid><description>Even trillion-dollar unicorns can be a house of cards when operating outside their core expertise.</description></item></channel></rss>