In recent years, there has been considerable debate about how AI could replace all of our jobs. For a long time I completely ignored the subject; most of it sounded like pure bu11SH1T. I had already studied neural networks and understood the basics of LLM, machine learning, deep learning, natural language processing and expert systems. I had even tried some generative AI tools, but none of them impressed me; They were buggy, full of hallucinations, and constrained.<\/p>\n
Last year (2024), I reviewed the topic more closely. A lot has changed, major improvements have been made, but still, nothing close to replacing a real software engineer, despite what many headlines suggested at the time.<\/p>\n
Since then, I have followed the field closely, conducting experiments and trying to understand how this technology could affect our daily work. Here’s how this experiment came to life: I decided to use AI solely to redesign the visual theme of my website (rafaelhs-tech.com). The idea was simple: change only the appearance of the site. That’s how it was.<\/p>\n
Technology stack<\/p>\n
I originally built my site in 2021 using Angular (version 7 or 8, I can’t remember exactly). It was pretty basic, just a few components with a space-themed design.<\/p>\n
The original version<\/p>\n
This was the original version. The journey with AI agents began with Claude 3.7. My first message was something like this:<\/p>\n
“This is an Angular XX application and I want to change the style to something with a cyberpunk theme. The folders are organized by components and each component represents a page.”<\/p>\n
Claude scanned the project, found the SASS files, and started generating new code… but then he started to freak out: he created React files inside an Angular project.<\/p>\n
I tried to fix it, but it kept drifting, breaking the app, mixing files, generating React code over and over again. So I scrapped everything and started over.<\/p>\n
This time, I was more specific: I mentioned the Angular version, described the folder structure, highlighted key files, and gave a complete overview of the project. The result? Slightly better visually, but the UI is still broken. Misaligned pages, inconsistent styling, and worst of all: the code was a mess.<\/p>\n
This type of departure was common. For those unfamiliar, mixing HTML, CSS, and JS in this way is bad practice in modern web development.<\/p>\n
It wasn’t exactly surprising, but it reinforced a key point: these agents still lack a real understanding of good development practices. I continued using Claude 3.7 for a while, but it became frustrating. I would ask for one thing and they would give me something completely different. After more than 15 prompts to align a single button, I realized it would have been faster to fix it manually, but I committed to simulating a non-technical user experience.<\/p>\n
I also tried CodeLLM, but it had another problem: it doesn’t retain long term memory. If the message fails or reaches the token limit, continuing on a new thread resets everything, out of memory from the previous context. That got really annoying.<\/p>\n
Common hallucinations with Claude 3.7:<\/p>\n
– I generated things that I didn’t ask for.<\/p>\n
– Changes could not be reverted<\/p>\n
– Removed everything and regenerated the code in loops.<\/p>\n
I then switched to Claude 3.5, which behaved more reliably. He followed instructions more precisely. I continued modifying things and finally got this result:<\/p>\n
The final version<\/p>\n
After about 40 prompts, I got a decent visual result. But the code was still messy: CSS mixed with SASS, inline JS with HTML, strange file names, useless comments… nothing reusable. I decided to try other LLMs like Gemini 2.5, GPT o1 and GPT o4mini. The result was the same frustrating one, with each run producing noticeably different results (as expected).<\/p>\n
Reflections<\/p>\n
There is no doubt that AI is changing the way we code, learn, and approach problems.<\/p>\n","protected":false},"excerpt":{"rendered":"
In recent years, there has been considerable debate about how AI could replace all of our jobs. For a long time I completely ignored the subject; most of it sounded like pure bu11SH1T. I had already studied neural netwo\u2026<\/p>\n","protected":false},"author":2,"featured_media":1038,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[],"class_list":["post-1037","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tech"],"_links":{"self":[{"href":"https:\/\/www.horoscopepath.com\/index.php?rest_route=\/wp\/v2\/posts\/1037","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.horoscopepath.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.horoscopepath.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.horoscopepath.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.horoscopepath.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1037"}],"version-history":[{"count":0,"href":"https:\/\/www.horoscopepath.com\/index.php?rest_route=\/wp\/v2\/posts\/1037\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.horoscopepath.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1037"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.horoscopepath.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1037"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.horoscopepath.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1037"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}