{"id":1873,"date":"2026-02-08T21:25:09","date_gmt":"2026-02-09T01:25:09","guid":{"rendered":"https:\/\/www.openbible.info\/blog\/?p=1873"},"modified":"2026-02-08T21:26:44","modified_gmt":"2026-02-09T01:26:44","slug":"last-week-an-llm-out-programmed-me","status":"publish","type":"post","link":"https:\/\/www.openbible.info\/blog\/2026\/02\/last-week-an-llm-out-programmed-me\/","title":{"rendered":"Last Week, an LLM Out-Programmed Me"},"content":{"rendered":"\n<p>With last week&#8217;s release of <a href=\"https:\/\/openai.com\/index\/introducing-gpt-5-3-codex\/\">Codex 5.3<\/a> and <a href=\"https:\/\/www.anthropic.com\/news\/claude-opus-4-6\">Opus 4.6<\/a>, I had a new experience: an LLM showed itself to be a better programmer than I am. If you&#8217;ve seen my <a href=\"https:\/\/github.com\/openbibleinfo\/\">code<\/a>, you may not think that&#8217;s a big achievement. But for the first time I saw, practically, how an AI could outperform me at something I take some measure of pride in. It was like Google&#8217;s <a href=\"https:\/\/www.openbible.info\/blog\/2025\/11\/virtual-archaeology-with-nano-banana-pro\/\">Nano Banana Pro moment<\/a>, but for coding.<\/p>\n\n\n\n<p>Unlike my previous experiences with LLM coding, Codex 5.3 didn&#8217;t just have more familiarity with the syntax of a language or the functionality of a module; it solved an architectural problem better than I did. (It reused existing file artifacts instead of creating intermediate files.) Likely it had pulled the architectural pattern from somewhere else, but it was an elegant solution&#8212;superior to the workable-but-basic approach I&#8217;d been planning. In that instant, I felt like the future had arrived in a small way: it was better at this task than I was, not just faster at it.<\/p>\n\n\n\n<p>LLMs have let me compress weeks of coding work into a few days. For the <a href=\"https:\/\/github.com\/openbibleinfo\/Bible-Passage-Reference-Parser\">Bible Passage Reference Parser<\/a>, I normally follow a six-month release schedule because changes take a lot of time, especially big refactoring changes like I&#8217;ve been planning for the next version (which moves language data to a different repo and adds an <a href=\"https:\/\/github.com\/openbibleinfo\/Bible-Passage-Reference-Parser-Languages\">additional 2,000 languages<\/a>). I&#8217;d been dreading this work for years because, with so many languages, dealing with exceptions would consume the bulk of the coding effort. I could barely manage exceptions with the 40 languages in the current repo, so adding 50x more didn&#8217;t sound fun.<\/p>\n\n\n\n<p>However, Codex 5.3 made short work of the task, taking a few minutes to accomplish what would&#8217;ve taken me days of dedicated work, not that I&#8217;d ever be able to dedicate days straight to this project. I published the <a href=\"https:\/\/github.com\/openbibleinfo\/Bible-Passage-Reference-Parser\/tree\/v4\">latest branch<\/a> five months ahead of schedule (and remember, the schedule is six months long).<\/p>\n\n\n\n<p>These models still make mistakes; you can&#8217;t yet let them code unattended. But their ability to plan ahead and write code according to that plan is now (at least sometimes) stronger than mine. A year ago, converting the reference-parser code from Coffeescript to Typescript involved a bunch of back-and-forth with ChatGPT; even with a straight 1:1 conversion, it still made questionable decisions that I corrected. With the latest models, LLMs are now correcting my questionable decisions.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>With last week&#8217;s release of Codex 5.3 and Opus 4.6, I had a new experience: an LLM showed itself to be a better programmer than I am. If you&#8217;ve seen my code, you may not think that&#8217;s a big achievement. But for the first time I saw, practically, how an AI could outperform me at [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[34,21],"tags":[],"_links":{"self":[{"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/posts\/1873"}],"collection":[{"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/comments?post=1873"}],"version-history":[{"count":11,"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/posts\/1873\/revisions"}],"predecessor-version":[{"id":1884,"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/posts\/1873\/revisions\/1884"}],"wp:attachment":[{"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/media?parent=1873"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/categories?post=1873"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.openbible.info\/blog\/wp-json\/wp\/v2\/tags?post=1873"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}