Automation & AI
All blog posts about automation (usually about n8n) and AI-related workflows and comments.
-
We're Making a Big Mistake
I believe that IT workers who are also passionate about gen AI are making a major misjudgment. We wrongly assume that the advances we observe in our field, such as the autonomous or semi-autonomous development of applications, also translate to sectors like medicine or law. This is a false generalization. The field of IT heavily relies on strict formalism: the raw material consumed by LLMs. In the legal field, for example, this is not the case: it is much more complex. Continue reading →
-
Matt Shumer writes in “Something Big is Happening”:
The AI labs made a deliberate choice. They focused on making AI great at writing code first… because building AI requires a lot of code. If AI can write that code, it can help build the next version of itself. A smarter version, which writes better code, which builds an even smarter version. Making AI great at coding was the strategy that unlocks everything else. That’s why they did it first.
Clever. Exciting. But scary, too.
-
The Rise of Cognitive Dept
Margaret-Anne Storey introduces “cognitive debt” as a concept that may be more threatening than technical debt in AI-augmented development. Unlike technical debt (which lives in code), cognitive debt is the erosion of shared understanding that resides in developers’ minds. Drawing on Peter Naur’s concept of a program as a “theory” distributed across teams, the article argues that as AI and agentic tools push for development velocity, teams risk losing their collective understanding of why systems work the way they do. Continue reading →
-
When I was a teenager, programming languages like LOGO made computers and programming very accessible. In today’s world, I would argue that, to some degree, vibe coding does the same: it makes computer programming more accessible in a much more complex digital landscape.
-
Anthropic cements its position as the not-OpenAI with no-ads pledge — The Register
Anthropic has committed to keeping its Claude AI model ad-free, emphasizing user trust and avoiding potential conflicts of interest that could arise from advertising. The company believes serving ads in chat sessions could introduce incentives that might compromise the AI’s helpfulness and neutrality, distinguishing itself from rivals like OpenAI who are exploring ad-supported models. This decision aligns with Anthropic’s principle-driven approach and focus on maintaining user privacy and genuine assistance.
How long will it last? In today’s tech world, cynicism prevails.
-
At this rate, I wonder if I could create a custom-build, highly feature-focused Inoreader replacement using Claude Code. My experience so far with RSS Flow seems to confirm that I could, piece-by-piece.
-
I’m putting the final touches on a few of my web apps before going on a two-week vacation. One nice thing is that my RSS Flow app can call my Microblog Poster app to quickly create a link post from a text selection in RSS Flow.
-
I’m not sure it was a good idea to put my GitHub repos inside iCloud Drive Documents folder. Some of my projects have more than 50K files inside of them, thanks to dependancies. The fileproviderd process consumes quite a lot of CPU cycles at times.
-
I’m learning so much non-AI stuff by using AI — BirchTree
a year into my AI-accelerated coding adventure, I am far, far, far more knowledgeable about development than I was when I started.
My experience with n8n, Claude Code, Vercel and GitHub in recent weeks not only exposed me to obscure things in web app development, but to useful use cases of generative AI.
-
Something Is Going On
I’m still working on this, but I’m heading in the right direction. I realize that every blog post should have a title so that my RSS flow feed looks great. 👀 Continue reading →
-
I'm rebuilding Flickr!
Well, maybe not, but here’s a description of my recently created photo-sharing webapp. And I have many more ideas to improve this. Photo Sharing WebApp - Feature Overview A modern, full-stack travel photo gallery built with Next.js 15, featuring intelligent photo management, interactive maps, and seamless cloud storage integration. 🌟 Highlights Zero-Database Architecture: Uses Vercel Blob for photos and Redis (via Vercel KV) for metadata Privacy Controls: Public, unlisted, and private album visibility options Interactive World Map: Displays photo locations extracted from EXIF GPS data Responsive Design: Optimized for all devices from mobile to desktop Admin Panel: Complete photo management without leaving the browser 🎨 Public Gallery Features Album Management Collapsible Albums: Each travel album can be expanded or collapsed independently Smart Defaults: Most recent album automatically expands on page load Album Metadata: Title, description, and date for each collection Privacy Levels: Public: Visible to everyone on the homepage Unlisted: Only accessible via direct link Private: Visible only to authenticated admins Photo Display Grid Layout Options: Three display modes to suit your preference Comfortable: Spacious 2-5 column grid with square thumbnails Compact: Dense 3-6 column grid for maximum photos per screen Masonry: Pinterest-style layout preserving original aspect ratios Layout Persistence: Grid preference saved in browser localStorage Newest First: Photos automatically sorted by upload date (newest at top-left) Rounded Thumbnails: Modern, elegant aesthetic with subtle shadows Hover Effects: Smooth scale and brightness animations on interaction Upload Date Display: Shows when each photo was added (in comfortable/masonry modes) Lightbox Viewer Full-Screen Experience: Distraction-free photo viewing Navigation Controls: Keyboard arrows (← →) for previous/next On-screen navigation buttons ESC key to close Photo Captions: Optional descriptions displayed below photos Smooth Transitions: Animated photo changes with loading states Mobile Optimized: Touch-friendly controls and responsive sizing Interactive Features World Map Integration: Leaflet-based interactive map Clustered markers for photos with GPS coordinates Click markers to view photos from that location Automatic bounds fitting to show all locations Album information in marker popups Random Featured Photo: Displays a random photo from all albums on homepage Changes on each page load Shows caption if available Mini Thumbnails: Collapsed albums show preview of first 5 photos Smooth animation on expand/collapse Photo count badge for albums with 6+ photos Content Syndication RSS Feed: Subscribe to new photo uploads at /feed. Continue reading →
-
Looking at my Micro.blog timeline summary I see this bad interpretation of my words in a recent post about updating my Nikon camera firmware from 1.21 to 3.0. 🤷🏻♂️🤦🏻♂️
-
“Please, add a map of all the places I visited based on photo metadata”. “Add animation across the site to make it more dynamic, nothing too fancy”. “Please, add support for progressive web app and make sure to set the favicon with the provided image”. “Add support for swipe gestures (ledt and right) while glancing at individual image”. “Add a counter of how many images are stored in each album”.
Are you getting it?
This is simple web app development in 2026 built using Claude Code, Vercel, Next.js and Tailwind CSS. 🤯
-
Building A Dedicated Photo-Sharing Website in Claude Code
Thinking about the upcoming trip to Egypt, I realized I still didn’t have a good solution for sharing photos and comments beyond the usual social networks. Drawing on my experience from the past few weeks deploying web applications on Vercel, I decided to try the same by building a website for sharing and viewing photos. The additional complexity here is that the viewing portion is separate from the photo upload section. Continue reading →
-
I completed implementing automated backups of all my n8n workflows to GitHub and documenting their triggering times in a compact format using Claude AI. The backup workflow is based on a template found in the n8n community.
-
This is how I glance at my Micro.blog timeline recently, using my n8n automation and my personal Discord server. The summary structure varies from one edition to another, likely due to the unpredictability of LLM on top of content variations. When something catches my interest, I go directly to the timeline or my timeline RSS feed to pick it up. I get these summaries every three hours. It’s fun.
-
Simon Willison on experimenting with Cowork from Anthropic:
“I had Claude Code reverse engineer the Claude app and it found out that Claude uses VZVirtualMachine - the Apple Virtualization Framework - and downloads and boots a custom Linux root filesystem.”
Whoa, this is clever. This is a reminder, too: my next Mac must have more than 16GB of RAM.
-
Anthropic on Cowork:
“That said, there are still things to be aware of before you give Claude control. By default, the main thing to know is that Claude can take potentially destructive actions (such as deleting local files) if it’s instructed to. Since there’s always some chance that Claude might misinterpret your instructions, you should give Claude very clear guidance around things like this.”
and
“You should also be aware of the risk of “prompt injections”: attempts by attackers to alter Claude’s plans through content it might encounter on the internet. We’ve built sophisticated defenses against prompt injections, but agent safety—that is, the task of securing Claude’s real-world actions—is still an active area of development in the industry. "
A world of possibilities awaits you. 🫣
-
On Apple’s Deal with Google
Back in November, Google announced Private AI Compute, positioning themselves to offer something like Apple’s Private Cloud Compute. It might be something that OpenAI wasn’t willing to do or didn’t see a fit in their business mission. By offering Private AI Compute, Google might have secured the business with Apple. Anyway, it’s becoming impressive how Google is taking back the lead in AI. Lastly, maybe we will see Google Gemini being added to this week’s next beta of iOS 26. Continue reading →