{"id":279,"date":"2026-09-02T22:28:41","date_gmt":"2026-09-03T04:28:41","guid":{"rendered":"https:\/\/xfebruary.fyi\/?p=279"},"modified":"2026-09-02T22:28:41","modified_gmt":"2026-09-03T04:28:41","slug":"crunchposting-on-ai","status":"publish","type":"post","link":"https:\/\/xfebruary.fyi\/?p=279","title":{"rendered":"crunchposting on AI"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">haven&#8217;t blogged in a hot second&#8230; work has me crunching really hard right now (14 hours a day, 7 days a week), so i need a bit of a pressure release, but i also can&#8217;t seem to spare the time to actually sit down and write out a rant without feeling the weight of the unfinished stuff flattening me and making it hard to breathe. part of my work involves pushing an AI TTS project through, and while i should make clear: contemporary LLMs are categorically all stochastic parrots and should be trusted about as far as you could feasibly throw a data center, regardless of how fine-tuned their system prompts are or how large their datasets are. USAmerican society&#8217;s general A) over-reliance on and B) HARD propagandizing of the technology is hugely disappointing. i have a LOT of thoughts on it but most of them boil down to the fact that technology should make our lives easier and AI does the opposite while pretending that it does exactly that. there is a reason it is the tool of the grifter and the hustler, and that is endemic in the promise it makes.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">it kind of epitomizes the current tech industry&#8217;s (and by extension USAmerican) perspective issue: short-sightedness. for immediate convenience, we are willing to burn the future; LLMs by necessity cannibalize the data is it is trained upon to generate &#8220;new&#8221; content, and by pumping the net full of the shit it&#8217;s producing, it is incestuously and inevitably going to swallow itself. i don&#8217;t know if we&#8217;ll ever see full-on model collapse, but already they are running low on new data to consume, and eating its own product is the death of the ouroboros.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">anyways, i was recently asked about my take on using AI for coding on LinkedIn, which is famously a site where you want to express your most employer-unfriendly opinions. here&#8217;s the question and my response. curious to know if i capitulated too much, or if you disagree! go to the comments!!!<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">LINKEDIN CONNECTION: I&#8217;ve heard varying opinions, but what are your thoughts on using AI to code? I know it&#8217;s super efficient for those who code every day, but I do worry if it is stifling my growth because AI truly makes it super easy. I just love asking people questions rather than solely depending on internet research.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">RESPONSE FOLLOWS:<br>I&#8217;ll be the first to admit to being a skeptic wrt generated code. It&#8217;s great if you just need a quick macro or script to organize some files or clean some data &#8212; that&#8217;s, to me, the equivalent of using a calculator to solve some math problems. Your ultimate goal in those instances isn&#8217;t to learn anything deeper about how those systems might work, you&#8217;re just accomplishing a task faster. But for serious applications, I&#8217;d feel a lot better knowing I can track provenance: where did this design pattern come from? Why was it used? Can I, if asked, explain the principles behind a choice I made?<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">I&#8217;ve been forced to use it to meet deadlines at work and I generally feel that while my programs are functional because of it, they&#8217;re not the same thing \/I\/ would make, and I usually spend just as long reprompting the model\/studying the new code to A) get what I actually want and B) be able to comprehend what changes were made. And the more complex a project, the more taxing prompting becomes: token consumption is higher because you&#8217;re feeding it more context to consider. There are no cookie-cutter solutions online for it to copy, and creativity is not one an LLM&#8217;s strong suit, so the odds that you get a dud response that fails to compile or doesn&#8217;t achieve what you want or misses an edge case increase sharply with complexity. You&#8217;d be better off dropping a StackOverflow code snippet that&#8217;s explained clearly into your code and having to do the legwork to integrate it, because at least then you&#8217;re intimately familiar with the process and can understand where points of failure might be occurring.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Those are the practical qualms I have with it anyways. There are also moral reasons to avoid using it: environmental impact, funding one of the biggest lobbying campaigns in DC currently, even the idea of stealing code if you&#8217;re concerned about IP&#8230; But even I can&#8217;t stick to being a Luddite forever; I have to concede they have their use cases, and when you&#8217;re in my shoes where I&#8217;m facing a totally new project and I&#8217;m the solo dev, it&#8217;s easy to rely on it as a code reviewer or idea &#8220;generator.&#8221;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">If I had my way I&#8217;d rewind the clock and have been born during the early boom of computers, but they haven&#8217;t invented a time machine yet.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>i was recently asked about my take on using AI for coding on LinkedIn.<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[34,35],"class_list":["post-279","post","type-post","status-publish","format-standard","hentry","category-musings","tag-ai","tag-work"],"_links":{"self":[{"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=\/wp\/v2\/posts\/279","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=279"}],"version-history":[{"count":2,"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=\/wp\/v2\/posts\/279\/revisions"}],"predecessor-version":[{"id":281,"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=\/wp\/v2\/posts\/279\/revisions\/281"}],"wp:attachment":[{"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=279"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=279"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/xfebruary.fyi\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=279"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}