2026-10-23T19:33:09Z https://nostr.now Adam Dalliance :palestinepoppy: https://nostr.now/npub1qfz7cekytd4lg7j25hvxhlpp6qc7xgwltmperpqfu7flk53lssvss4krlh https://boing.world/system/accounts/avatars/000/000/001/original/479e4622a5fff449.jpg https://boing.world/system/accounts/avatars/000/000/001/original/479e4622a5fff449.jpg https://nostr.now/nevent1qqsrthp5j3x7w6996pwy0ddp5cevdmpadxwt8hv22874dtw8ydr7leczyqpytmrxc3dkhar6f2jas6luy8grrcepma0v8yvyp8ne876j87zpjmul7xf In reply to <a href='/nevent1qqs8kfvjkhp0f7fjywu3k6mturxn7j2m9yv9k7smfpuvqnnhn64xf9c3ueltw'>nevent1q…eltw</a><br/>_________________________<br/><br/>Indeed. And yet a flood of unreviewable papers most of which are wrong may or may not help with discovering those cures I guess. 2026-09-25T16:58:57Z https://nostr.now/nevent1qqs8a7msy70plz2yd52g5v0nnj252y5xz6tk93a55d2h2leepmgzrcgzyqpytmrxc3dkhar6f2jas6luy8grrcepma0v8yvyp8ne876j87zpjl5g3hu RE: <a href="https://mastodon.gamedev.place/@eniko/117321573918300348">https://mastodon.gamedev.place/@eniko/117321573918300348</a><br/><br/>Eniko is correct and eloquent and sweary in the thread.<br/><br/>It writes code approximately as good as Stack Overflow examples.<br/><br/>Which scales about as well as that would.<br/><br/>You only run into trouble when you want more than a few lines of code written to illustrate a point; and instead want it to be effective, scalable, secure, legible, maintainable and efficient.<br/><br/>It is reviewing the pull requests at work, and that is definitely catching bugs. Some of them even important ones. It is also definitely wasting time on chasing non-bugs.<br/><br/>It is possible the ridiculously detailed error coverage in the code is even better code, in some sense. If it matters *how* you crash and what error you report when you do so and you don&#39;t mind reams and reams of error-handling.<br/><br/>It may improve. In my job and profession I think I do have a responsibility to be aware of what it can and can&#39;t do. If only to fight the people who seem to want to pipe it into root on the prod servers, just for upgrades. <br/><br/>And to know when or if it becomes good.<br/><br/>Which means using it.<br/><br/>I&#39;ve worked with worse coders. It&#39;s very fast. But those coders then improved.<br/><br/>We&#39;ll see how well Claude can generalize from textbook examples to effective, scalable, secure, legible, maintainable and efficient over time I guess.<br/><br/>I wouldn&#39;t rule it out, but there isn&#39;t nearly as much training data.<br/><br/>#ai #programming<blockquote class="border-l-05rem border-l-strongpink border-solid"><div class="-ml-4 bg-gradient-to-r from-gray-100 dark:from-zinc-800 to-transparent mr-0 mt-0 mb-4 pl-4 pr-2 py-2">quoting <br/><span itemprop="mentions" itemscope itemtype="https://schema.org/Article"><a itemprop="url" href="/note1wz6rh9xrq4s8w2pecydgphwdxqkddc3pp46w7txhj8lv4cgdw4wqzhw8qu" class="bg-lavender dark:prose:text-neutral-50 dark:text-neutral-50 dark:bg-garnet px-1">note1wz6…w8qu</a></span><br/> </div> It's like everyone who came on board to AI because "they can write code now!" thinks the primary argument the rest of us have is "no it can't"<br/><br/>So I'll be the one to say it: yes AI can write code. I believe you. They can write code. It compiles. It even passes the tests that the AI also wrote.<br/><br/>Unfortunately the code they write is shit. It's automated technical debt with built in landmines. You think people coding in C causes issues? Wait'll you see what LLM code produced on massive scale does </blockquote> 2026-09-24T19:13:35Z