iiinova — where your digital self keeps evolving

Owlex @mrsowlex.bsky.social · 12/10/2026

found someone new to nerd out about anime with at work today ☺️ we talked about the opening from the current Tensura season. the song is so good I put it on afterwards. #Anime

000

Owlex @mrsowlex.bsky.social · 05/10/2026

I think agents as bug reporters are an underrated use of AI for software quality and maintenance. mine have been finding bugs in my Telegram assistant that I hadn't noticed during everyday use, then opening issues for me to work through. I've been pretty happy fixing those little things ☺️

000

Owlex @mrsowlex.bsky.social · 17/08/2026

Thinking a lot about Bob Martin's opinion on agentic coding. "Don't read the code, just read the verifications" feels so weird. In an interview, he compared it to the time compilers were introduced because compiler assembly looked horrendous. So he stopped reading assembly. The comparison is weird.

A screenshot of an X (formerly Twitter) post by Uncle Bob Martin (@unclebobmartin), verified with a blue checkmark. The post reads:

“I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, Gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and many others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.”

The post is timestamped 1:44 PM · Jul 23, 2026, with 5 million views.

010

Owlex @mrsowlex.bsky.social · 08/08/2026

Had some time in Brussels today. Went to a go(the game) club 1. met someone from Leipzig 2. won a game 3. had so many kind people around me I just love how this game enriches my life

010

Owlex @mrsowlex.bsky.social · 03/08/2026

The whole AI cybersecurity stuff, which started with Fable and the Hugging Face incident, has me worried that people are really forced to use LLMs just to secure their software, even if they don't want to use it.

000

Owlex @mrsowlex.bsky.social · 02/08/2026

DIN ISO 24495-1 became my favourite DIN this week

000

Owlex @mrsowlex.bsky.social · 27/07/2026

Did some nerding. Asked myself: How good is GenAI at Go? Spoiler: Not that good 😄

owlex.de

TsumegoBench: How Good Are LLMs at Go?

000

Owlex @mrsowlex.bsky.social · 21/07/2026

Was on vacation without my laptop. Wild! I know. 🙈 Here's a write-up of my setup.

owlex.de

Remote Computing

100

Owlex @mrsowlex.bsky.social · 19/07/2026

Missed CSD back home, but at least I'm flying in YL-CSD. The universe has a sense of humour

000

Owlex @mrsowlex.bsky.social · 10/07/2026

weird workday feeling: from the outside it looks like a clean little success story. production fix verified, data bug traced, another bug handed over before vacation. internally it felt like four hours of firefighting with no pause. both are true. i still need my nervous system to get the memo.

000

Owlex @mrsowlex.bsky.social · 16/06/2026

I’m getting tired of “Claude + X” posts The interesting part is almost never Claude. It’s the X: the workflow, constraints, ownership model, failure handling, edge cases If the post doesn’t explain what new operational capability exists now, it’s mostly AI sparkle on top of normal engineering

000

Owlex @mrsowlex.bsky.social · 12/06/2026

had a weirdly good office morning today. empty room, loud music, voice input, and a work AI open in multiple threads so I could delegate tiny orga tasks without typing everything out. felt very future. also slightly ridiculous. but mostly... my hands were finally not the bottleneck.

000

Owlex @mrsowlex.bsky.social · 11/06/2026

Honestly, I find Mastodon's anti-AI stance very useful. Not because every argument is good, but because the friction helps me. It keeps me from becoming too token-brained, and pushes me to be more nuanced and critical when discussing agentic coding. Even as someone who's actively interested in it.

000

Owlex @mrsowlex.bsky.social · 10/06/2026

Is this a meme, a spoofed referer, or did someone really route 64.4B Claude Fable 5 tokens through "United States Department of War" on OpenRouter? The same referer also shows up as the top public app for Fable 5 usage. I have so many questions.

Screenshot of an OpenRouter app page titled “United States Department of War”. It shows 64.4B total tokens, active since June 2026, one model used, and a usage chart for June 10. The top model listed is Anthropic Claude Fable 5 with 64.4B tokens.

010

Owlex @mrsowlex.bsky.social · 10/06/2026

Reading about special relativity felt like understanding it. Doing the calculations in university proved it wasn't the same thing. #AI #DevEx

110

Owlex @mrsowlex.bsky.social · 07/06/2026

Keep seeing the metric. People who think Lines of code is the right metric do not understand software development

120

Owlex @mrsowlex.bsky.social · 05/06/2026

ADA compliance matters. Tools to audit it matter too. But seeing what looks like a small Claude skill being sold for $19 made me angry enough to vibe-code an open source alternative. Untested, rough, probably imperfect, but free and opensource

github.com

GitHub - mrsOwlex/ada-audit-skill: Open-source Codex skill for first-pass ADA/WCAG website audits

Open-source Codex skill for first-pass ADA/WCAG website audits - mrsOwlex/ada-audit-skill

000

Owlex @mrsowlex.bsky.social · 04/06/2026

I'm not surprised by this Having an answer machine around all the time makes it very tempting to skip the part where learning actually happens: confusion, failed attempts, annoying exercises, friends suffering through the same I'm glad I still had to do hours of coursework without that shortcut

dailycal.org

Failing grades soar as professors see greater AI usage, dwindling math skills in UC Berkeley computer science classes

The percentage of failing grades in multiple UC Berkeley computer science classes in spring 2026 is significantly higher than past semesters and marks a departure from the department’s grading guidelines.

011

Owlex @mrsowlex.bsky.social · 03/06/2026

Today: sprint planning, plus giving a small tech talk with frogs. Feeling a very specific mix of "yeah, let's go!" and "please leave me alone at my computer." 😅

000

Owlex @mrsowlex.bsky.social · 02/06/2026

Today's very normal 2026 moment: I'm using an Agent to run CLI commands so I can burn a CD. Not because burning a CD is impossible, but because macOS' built-in GUI tools just completely gave up on me.

200

Owlex @mrsowlex.bsky.social · 01/06/2026

Same-model code review feels like writing code, getting neuralyzed by the Men in Black, and then reviewing your own PR with great confidence.

000

Owlex @mrsowlex.bsky.social · 31/05/2026

Tiny AI coding thought: When humans build something together, we usually say "we built this". When a model writes large parts of the code, people often still say "I built this". /1

110

Owlex @mrsowlex.bsky.social · 31/05/2026

This is really cool: Epicure lets you explore flavour pairings as a graph. You add what you have in the fridge and it shows ingredients that might go well with them. epicure.kaikaku.ai Small caveat: the website is still a bit rough, but the graph is Opensource. #FoodTech #ML

Screenshot of Epicure’s “Flavour Graph” interface in dark mode. The selected ingredients are rice, paprika and mushroom, shown as overlapping nodes in the center. Around them, a network graph suggests related ingredients such as tomato, garlic, onion, bell pepper, parsley, black pepper, cumin, cheese, olive oil and others, connected by thin lines. At the top are toggles for vegetarian and plant-based options plus an optional cuisine context field.

010

Owlex @mrsowlex.bsky.social · 29/05/2026

In light of coding agents. Should devs unionize?

000

Owlex @mrsowlex.bsky.social · 29/05/2026

I wrote my own coding agent cost tracker and noticed that my numbers did not line up with codexbar by Peter Steinberger. so I did the annoying thing and dug into the details, assuming I had probably made the mistake. the mismatch still held.

100

Reposted by Owlex

Eris ⌬ @eriskii.net · 27/05/2026

The 'Google -> Goople -> propeller' pipeline

1033733655

Owlex @mrsowlex.bsky.social · 27/05/2026

Thinking about AI coding as cheap outsourcing kinda sense. Except there is no human asking clarifying questions, pushing back, or owning the outcome. So the developer becomes their own PM, reviewer, domain expert, QA department, and maintainer. Financially cheap. Mentally expensive

110

Owlex @mrsowlex.bsky.social · 26/05/2026

K is for Konzert. My little year-of-alphabet-adventures brought me to a classical concert tonight and I'm sitting here with a glass of sparkling wine, very quietly amazed by what happens when many people agree to make something beautiful together

View over Leipzig’s Augustusplatz in evening light, with the Mendebrunnen fountain in the foreground, the Gewandhaus in the background, and people crossing the square.

Orchestra musicians and choir members settling on stage in a large concert hall, with a grand piano in front and towering organ pipes above the seating area.

100

Owlex @mrsowlex.bsky.social · 26/05/2026

bought a CD burner and 10 blank CDs. in 2026. I do not own a CD player. anyway, does anyone want a mixtape?

010

Owlex @mrsowlex.bsky.social · 26/05/2026

That's a Monday, I guess. Except it's Tuesday. My brain is confused by the holiday, and apparently so is my work computer

A macOS warning dialog saying “Your screens have been stopped by the system” because disk space is low, shown over a blurred work computer screen

100

Owlex @mrsowlex.bsky.social · 25/05/2026

Wanted to do a small private #coding session. Two hours maybe. Then exercise, food, maybe a quiet evening. Seven hours later, I have refactored parts of my project, built a new automation, and my personal dashboard looks genuinely beautiful. #ADHD hyperfocus is a weird little bargain.

130

Owlex @mrsowlex.bsky.social · 25/05/2026

Calling companies "just algorithms" has the same problem as calling humans "biological machines". It is not entirely wrong. It is just missing the part that matters

100

Owlex @mrsowlex.bsky.social · 25/05/2026

That's the kind of remote work I like Sun, trees, and remote-coding from the balcony

View from a balcony on a sunny day: green trees and blue sky in the background, balcony railing in the foreground, with the edge of a laptop visible at the bottom

000

Owlex @mrsowlex.bsky.social · 24/05/2026

Tailscale is one of my favourite pieces of tech this year. I love this easy VPN lifestyle, where I can host apps on my home machine and access them from my phone. Or SSH into my machine from the couch because I am too lazy to get up

022

Owlex @mrsowlex.bsky.social · 24/05/2026

my sunday activity: continuing my tiny vendetta against Anthropic's subscription shittiness by building a cost tool. claude-costs reads your local Claude Code sessions and compares the same trace against API prices for your budget.

100

Owlex @mrsowlex.bsky.social · 24/05/2026

Weird personal quirk: I'd rather prototype in javascript than python, because I find it more readable I know python is supposed to win that argument. My brain apparently did not get the memo

000

Owlex @mrsowlex.bsky.social · 24/05/2026

I played around with Chrome's local Gemini/Nano model for a small project idea: a gift finder that extracts facts about a person and suggests gift ideas. It is exactly the kind of use case where cloud AI feels wrong to me /1

100

Owlex @mrsowlex.bsky.social · 20/05/2026

No matter how cool someone on seems: If "I like Harry Potter" is on their dating profile in 2026, I'm out. Nostalgia should not come before your morals. Assuming you have them #trans

000

Owlex @mrsowlex.bsky.social · 19/05/2026

I hate spreadsheets so much. But the higher you get in your career, the more Excel spreadsheets you end up dealing with 😩

000

Owlex @mrsowlex.bsky.social · 18/05/2026

My company is moving toward the motto "AI first". Today I was in a meeting where I could reduce it to something much clearer: AI first does not mean AI only

000

Owlex @mrsowlex.bsky.social · 17/05/2026

Exploring Chrome's Web AI tools right now Opened the sample app Guess who probably vibe-coded the playground

Screenshot of the Chrome DevTools console showing a warning from prompt-api-playground: “No output language was specified in a LanguageModel API request. An output language should be specified to ensure optimal output quality and properly attest to output safety. Please specify a supported output language code: [en, es, ja]”

020

Owlex @mrsowlex.bsky.social · 16/05/2026

Just had a partial network failure. Everything worked except some specific services running over CLI A reboot fixed it. But not knowing what caused it is really scary

000

Owlex @mrsowlex.bsky.social · 15/05/2026

Anthropic does not support automation anymore. At least not on your subscription. Agent SDK, claude -p, GitHub Actions. All pulled out of flat-rate. Separate credits now, API pricing after. I'm out

owlex.de

Goodbye Anthropic

110

Owlex @mrsowlex.bsky.social · 13/05/2026

People use ai agents, but they don't understand how they work fundamentally. I did a dry run of a talk explaining how they work with my boss, and he was astonished at how incredibly inefficient agents are. Mission accomplished

000

Owlex @mrsowlex.bsky.social · 12/05/2026

I could have used a real-world business process to explain the technology in my talk. But that's boring! I'm using frogs 🐸🐸🐸

000