Automation & AI
All blog posts about automation (usually about n8n) and AI-related workflows and comments.
-
I completely put aside OpenClaw experimentation since its creator went to OpenAI. It’s not about OpenAI owning the thing, which seems it’s not the case, I simply decided to let the thing mature while I’m finishing my other projects which consume a lot of AI credits anyway. I’ll get back to it eventually.
-
It’s a good start. Looks quite different than my other web app. Still a lot to implement.
-
Working on my future bookmarks manager webapp. I’m still refining the specs document. I decided to add the possibility to save text quotes in addition to bookmarks. Quotes might be linked to a bookmark. My specs document is quite long and detailed. I wonder how good Claude Code will be to digest all this from the start.
-
Done. I exported my ChatGPT memory to Claude. I’m curious to see how Claude’s answers to my prompts will change from now on. Starting March 12th, I’ll be on Anthropic / Claude AI only.
-
Currently assessing the impacts of unsubscribing from ChatGPT. Image creation is the most obvious impact, but I rarely use it. I could switch to MidJourney for a third of the monthly price. API consumption is another factor, but none of my four API keys have been used in the last 30 days. According to Claude AI’s examination of my current n8n workflows, three are configured with an OpenAI API key. Investigating further.
-
Since when is this a thing: Switch to Claude? I mean, I wrote “A Case for ChatGPT Takeout” not long ago!
Moving out of ChatGPT / OpenAI is now a movement, right?
-
I use AI coding assistants extensively, but I don’t vibe code
I do too, but I’m not sure to understand the difference.
-
I would love to build the dream bookmark manager for myself, just like I built an RSS reader and a photo-sharing website. I love AnyBox, but it’s not integrated with the rest of my workflow and doesn’t have a web version. This bookmark manager could be integrated into my RSS reader and gather data from Micro.blog Bookmarks, too. Still a lot to think about.
-
While waiting for Micro.blog next chapter, I’m playing with RSS feeds display strategies. This view is called “Journal”. Built using Claude Code and hosted on Vercel.
-
Building a custom branded Ghost theme for my main website with the help of Claude Code seems like an achievable goal, right?
-
The speed at which Anthropic is adding new stuff to Claude and Claude Code on the desktop is impressive. Is OpenAI even competing?
-
Early this morning, using Craft Agents, I created a new skill that enables me to save my Micro.blog Bookmarks into a Craft collection. The agent figured out the Micro.blog API, the new collection schema and how to move things around. So cool. Any questions?
-
At this point, I have to admit, the only reason I’m keeping ChatGPT is its image-generation and analysis capabilities.
-
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.
