From 4dff1b11e5ef93e8748ced101b0bf6ab76e9791d Mon Sep 17 00:00:00 2001 From: Nate Anderson Date: Wed, 3 Jun 2026 00:10:16 -0600 Subject: [PATCH] Add quality ai post --- .aspell.en.pws | 3 + .../25-01-28-ai-hestiation-turning-around.md | 4 +- content/posts/26-06-02-the-'quality'-of-ai.md | 56 +++++++++++++++++++ 3 files changed, 61 insertions(+), 2 deletions(-) create mode 100644 content/posts/26-06-02-the-'quality'-of-ai.md diff --git a/.aspell.en.pws b/.aspell.en.pws index 769d05a..5f62877 100644 --- a/.aspell.en.pws +++ b/.aspell.en.pws @@ -7,6 +7,7 @@ anon's Anthropic ASMR aspell +backend bluetooth Bly btw @@ -57,7 +58,9 @@ Kimber kombucha lastmod LDS +libre linux +LLM's lobste localhost lol diff --git a/content/posts/25-01-28-ai-hestiation-turning-around.md b/content/posts/25-01-28-ai-hestiation-turning-around.md index 036c4a3..1a19ddb 100644 --- a/content/posts/25-01-28-ai-hestiation-turning-around.md +++ b/content/posts/25-01-28-ai-hestiation-turning-around.md @@ -1,8 +1,8 @@ --- date: 2025-01-28 description: "I realized that I've been holding myself back because of pride." -lastmod: 2025-01-28 -showTableOfContents: true +lastmod: 2026-06-03T00:08:31-06:00 +showTableOfContents: false tags: ["ai", "reflection"] title: "AI Hesitation Turning Around" type: "post" diff --git a/content/posts/26-06-02-the-'quality'-of-ai.md b/content/posts/26-06-02-the-'quality'-of-ai.md new file mode 100644 index 0000000..cefc31f --- /dev/null +++ b/content/posts/26-06-02-the-'quality'-of-ai.md @@ -0,0 +1,56 @@ +--- +date: 2026-06-02T23:35:33-06:00 +description: "In the height of LLM's" +# image: "/images/" +# image_caption: "" +# image_alt: "" +lastmod: 2026-06-03T00:08:31-06:00 +showTableOfContents: false +tags: ["ai","aesthetics","philosophy"] +title: "The 'Quality' of Ai" +type: "post" +draft: false +--- + +[The blog post that got me to put my words down](https://sinclairtarget.com/blog/2026/06/01/quality-in-the-age-of-slop/). + +[Last year](../25-01-28-ai-hestiation-turning-around) I decided to give AI a shot. Previous to that, I had dabbled with the chat interfaces of Claude and ChatGPT, but +had resisted really diving in. + +Just so no one doubts my 'allegiance', or to brand myself into the camp of water-boilers, over that time span I have: + +- Fully vibe-coded a web-rtc baby monitor (flutter app and Go backend) + - I've vibe-coded or AI assisted many other projects, but that was the most substantial project that works. +- Paid for various subscription services (Claude) for said vibe coding +- Used tons of chatting with AI to plan projects, make recipes, research things on my mind +- At work, used Opencode to complete many of my work tickets, typically iterating in Plan mode, then executing said plan + - No Pr's were ever merged without some minor intervention as far as I recall, there was always a little something here or there that needed tweaking, but it definitely felt very productive. +- See-saw'd every week between "this is awesome" and "I'm pretty sure I'm getting dumber and need to stop" + +I feel I have fully submerged myself in the slop swamp. What have I learned? + +## LLM's are Excellent + +Large Language Models are really cool piece of technology. I hope one day there is a fairly and freely (as in libre) +trained model to replace search. It is so nice to "describe" what you are searching when you only have the vagaries in +your mind. Turning English text prompts into random statistical output is a wildly cool idea. + +_Unfortunately_ + +It is so very problematic. + +## LLM's are Evil + +I think my experiment with going all-in with LLM's has taught me just how insidious this technology can be. I believe it +has [wreaked havoc in many peoples' lives (Wikipedia)](https://en.wikipedia.org/wiki/Deaths_linked_to_chatbots). I feel +that the price a software engineer pays to have a prediction engine produce the code for them is steep. It erodes +personal expertise, cheapens the craft and love of the craft, sucks the enjoyment out of work, and steals the ability to make any large maintenance decisions with confidence. + +I feel that my original aversion to these programs was right. The technology inserts itself (by default) in the loop, creating +dependence. + +LLM's do not produce Quality, they cannot. So, I think I am done with AI code assistance. Rubber ducking and search still +seem very helpful to me, so I'm going to try and move to self-hosted models for those use-cases. + +I want to continue to improve my craft. I want to love this craft. It's why I started down this road nearly ten years +ago in college.