Automation & AI
All blog posts about automation (usually about n8n) and AI-related workflows and comments.
-
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 →
-
I just discovered that Raindrop.io offers many integrations, including n8n! I might need to reconsider my bookmarking strategies, yet again. I’m currently using Anybox. 🤔 I’m exploring ways to move the data around. If you made a similar move, I’ll be more than happy to learn about your experience. For now, I’ll prompt ChatGPT for strategies.
-
This diagram tries to illustrate the how modern AI, Claude AI in particular, compares to traditional computing paradigm. Models more or less are processors, Agents are more or less the operating system and Applications are more or less Skills. It’s interesting, but I’m wary about agents because they open up too many pandora boxes.
-
I made two important changes this morning for my automation-related operating environment:
- Using DigitalOcean monitoring, I created two resources alerts (CPU > 50% for 5 min, Disk usage > 70% for 5 min). Alerts will make me look into n8n automation misbehaviours.
- I switched my AI nodes to use Claude AI Haiku 4.5 instead of Sonnet 4.5 to reduce costs for comparable results. I don’t think my summarization tasks needs more powerful LLM.
-
When Things Go Wrong With AI-Generated Code
My first bad experience: the code generated by Claude Code made my dashboard unresponsive in my browser. Eventually, the data stopped updating. After a ten-minute debugging session, I asked Claude Code to revert the change, and it did so promptly. But then I started getting execution failure notices on Discord. A lot of notifications. Then I started investigating… It appears the browser was making frequent refresh requests to one of my workflows, which depleted my Claude pay-per-use credits. Continue reading →
-
I’m making good progress on my personal dashboard idea. While people may criticize LLMs and enjoy coding for fun, for me, it opens up possibilities I couldn’t have imagined before.
-
One of the frustrating aspects of LLMs is their lack of consistency unless you develop specific skills, which can take time to implement effectively. For example, I wanted to generate documentation for my most recent n8n automation workflow, but Claude was unable to do it, and I can’t remember the prompt that finally made it possible. I should have saved it somewhere for easy retrieval. I’m wasting precious credits. 🤦🏻♂️
-
Simon Willison on AI-assisted programming:
The more time I spend on AI-assisted programming the less afraid I am for my job, because it turns out building software - especially at the rate it’s now possible to build - still requires enormous skill, experience and depth of understanding.
-
In today’s world, with LLM, Claude Code, etc., is Apple’s Swift Playground still relevant, even for younger aspiring coders? A few years ago, it seems we were hearing much more about it than today.
-
Apparently, people are barely using Stack Overflow to ask questions, thanks to LLMs and AI. I expect a similar trend among people in a community like this one on Micro.blog. Some questions would be super easy to answer by asking ChatGPT or the like. I do understand that many people still want this human touch, though.
-
Updated my n8n instance from v2.0.3 to v2.2.4. Super easy to do (I’m using the Docker Compose installation provided by the DigitalOcean 1-click install droplet. Took a droplet snapshot before, just in case something goes wrong. So far, so good. Of course, Claude helped me out on this. I’m not a Linux or Docker expert. 😅
-
Claude Code skills are probably the most intriguing aspect of Claude Code and Claude AI. I’m not so sure yet how to take advantage of them. My understanding from this excellent video is that you have to be an expert at something to create those skills.md file.
-
An Important Lesson
When I started my studies in computer science over 40 years ago, we learned to read functional specifications and then translate them into machine instructions (COBOL, FORTRAN, Pascal, etc.). It was the training of a programmer. I knew that one day I could become the person who writes functional specifications. I didn’t become a programmer, nor did I work in the development world. Due to my recent experience with Claude AI, Claude Code, and Vercel to create custom applications, I realize that I have become the one who writes functional specifications, but for processing by artificial intelligence. Continue reading →
-
Added a new and much-needed feature to my micro.blog front end. See my prompt below.
