2026-07-23T01:43:56Z https://njump.me Ted M. Young https://njump.me/npub1l0qq4ruptf4xg7pfnl33q5llnffz7e95dwynllq6rpju72s6wm5s5f7r2w https://files.sfba.social/accounts/avatars/109/253/958/480/151/940/original/f153b53935f21575.jpeg https://files.sfba.social/accounts/avatars/109/253/958/480/151/940/original/f153b53935f21575.jpeg https://njump.me/nevent1qqsgqrh0ka3w8kn6qradjcp9tu4c8dy4qvx6ag6s2as867pg8r0gmdszyrauqz50s9dx5erc9x07xyznl7d9ytmyk34cj0lurgvxtne2rfmwjkaw4pn Getting tired (again) of every conversation ending up talking about “AI”. Got testy on my stream cuz someone said I was being “sensitive” about it, but it was more that I was just plain tired of talking about it. (and trying to steer the conversation to whether “AI” can be conscious did NOT help their case)<br/><br/>I need to start declaring “AI” as being verboten on at least some streams. 2026-07-10T23:39:03Z https://njump.me/nevent1qqsymrckfn3lxxxdfxe33tv43kxmzrzm0q258va90weg0zkptujdt0szyrauqz50s9dx5erc9x07xyznl7d9ytmyk34cj0lurgvxtne2rfmwjvltzd6 I&#39;ve seen comments about accepting LLM-generated code in that we don&#39;t/can&#39;t understand it and excusing that because:<br/><br/>&#34;There&#39;s always code in the system that we don&#39;t understand&#34; 2026-06-21T17:31:14Z https://njump.me/nevent1qqsrecwamlncmh0swu9cfc40pk93hl307e6hs5shttfkukhwgml3c7czyrauqz50s9dx5erc9x07xyznl7d9ytmyk34cj0lurgvxtne2rfmwjxknlw4 In reply to <a href='/nevent1qqsymrckfn3lxxxdfxe33tv43kxmzrzm0q258va90weg0zkptujdt0sqegqh3'>nevent1q…gqh3</a><br/>_________________________<br/><br/>Except, LLM-gen&#39;d and human-written code are different.<br/><br/>One was written by someone with a mental model. Modified by humans with another mental model (correct or not), etc.<br/><br/>The other is generated by statistical, stochastic methods with constraints.<br/><br/>These are not the same. 2026-06-21T17:31:14Z https://njump.me/nevent1qqsps8s0a23w8n76uyqwu2lj4q20m4qfzm60n7qwn324nerc6g3sg7szyrauqz50s9dx5erc9x07xyznl7d9ytmyk34cj0lurgvxtne2rfmwj9nkz88 In reply to <a href='/nevent1qqsrecwamlncmh0swu9cfc40pk93hl307e6hs5shttfkukhwgml3c7clwz8tw'>nevent1q…z8tw</a><br/>_________________________<br/><br/>Want to use LLM-generated code? That&#39;s your choice. But don&#39;t argue that it&#39;s the same as code from 15 years ago, written by folks who had a human mental model, and made sense to them at the time. 2026-06-21T17:31:14Z https://njump.me/nevent1qqsx8t87pqnxudvwfqrldl062fvsp7rnp9y3j4gun6hqtt5rcgrsmaszyrauqz50s9dx5erc9x07xyznl7d9ytmyk34cj0lurgvxtne2rfmwj3skdpx The argument made by some folks regarding LLMs being non-deterministic is that humans are non-deterministic as well. However, humans are non-deterministic in a particularly human way. Also, humans can (usually) explain themselves (at least in terms of why they chose some particular solution), but LLMs cannot explain their output (despite appearances), since it’s stochastic, with no underlying meaning. 2026-02-23T20:36:54Z https://njump.me/nevent1qqs9853ecj7qez8r92uz37449xxhrs8ljgt8ku544rexr87jq5n0drczyrauqz50s9dx5erc9x07xyznl7d9ytmyk34cj0lurgvxtne2rfmwjru95m6 8.35 mile run this morning and NO PAIN. Hallelujah.<br/><br/>I&#39;ve been testing out new foot cushioning to deal with apparent sesamoiditis and today was planning on running 7 miles, but felt so good I just kept running.<br/><br/>#Running 2024-06-15T20:08:35Z https://njump.me/nevent1qqsfpyrdnaq8ge8gx57g942ukfkx0dquqdqjvqnmrl4c3g7q780vmaqzyrauqz50s9dx5erc9x07xyznl7d9ytmyk34cj0lurgvxtne2rfmwjn9cakd In reply to <a href='/nevent1qqsg80f30kk8v0e3fxtnsxfcyjumrhhg7zvh9r735y9u7650vqyku6qn72auc'>nevent1q…2auc</a><br/>_________________________<br/><br/>Otherwise, I recommend you treat all ideas (mob/ensemble programming, trunk-based development, TDD) as potential experiments that you can run, trying out those techniques.<br/><br/>You can&#39;t read your way to doing things better, instead you have to experience ways of doing things and give those experiments an _honest_ try, not &#34;well, we tried it once and didn&#39;t like it&#34;. How many new things that improved the way you did things did you like on the first try? 2024-06-02T19:26:17Z https://njump.me/nevent1qqsg80f30kk8v0e3fxtnsxfcyjumrhhg7zvh9r735y9u7650vqyku6qzyrauqz50s9dx5erc9x07xyznl7d9ytmyk34cj0lurgvxtne2rfmwjp5cl74 If you&#39;re asking for papers in published journals as evidence before you try out a technique or process in software development, first ask if your CURRENT way of working has such evidence and support.<br/><br/>#ExperimentOverEvidence 2024-06-02T19:16:08Z