ESE 2026-Kongress-Selektor – ๐๐ฌ๐-๐๐๐ฌ๐ ๐รผ๐ซ ๐๐ฎ๐ฌ๐ญ๐จ๐ฆ ๐๐-๐๐๐ฌ๐ข๐ ๐ง
Zu Beginn die Klรคrung, dass ich weder mit dem Embedded Software Kongress verbandelt bin, noch bezahlt wurde etc.
Ich wรผrde gern dieses Jahr nach Sindelfingen reisen, also war es Zeit, die Agenda zu studieren. Die Webseiten bieten einen guten รberblick.
ABER: Sie kรถnnten etwas komfortabler in der Bedienung sein. Denn fรผr eine fundierte Entscheidung brauche ich die Info, was der Vortrag neben der spannenden Headline wirklich aufzeigen mรถchte. Jeden Vortrag im neuen Tab รถffnen und laden lassen? Nee, bitte nicht. Ebenfalls: eine Vorselektion fรผr die fรผr mich relevanten Bereiche: ๐๐ซ๐จ๐ฃ๐๐ค๐ญ- ๐ฎ๐ง๐ ๐๐๐๐ฆ-๐๐๐ง๐๐ ๐๐ฆ๐๐ง๐ญ, ๐๐ ๐๐ง๐ญ๐ข๐ ๐๐, ๐๐ค๐๐ฅ๐ข๐๐ซ๐ฎ๐ง๐ .
Also schnell den ๐๐๐_๐๐จ๐ง๐ ๐ซ๐๐ฌ๐ฌ_๐๐๐ฅ๐๐ค๐ญ๐จ๐ซ (https://github.com/marcelpetrick/ESE_Kongress_Selektor) in #Python implementiert.
Was brauchen wir hierfรผr? Einen #Scraper und eine statische Webseite. Der Export der Selektionen erfolgt via JSON. Die Struktur der Seiten wird mehr oder weniger รผbernommen.
Rasend schnell, Details zum Vortrag werden via Tooltip (statt auf einer neuen Seite) angezeigt, Filterung ist mรถglich.
Repo klonen und die ๐ฑ๐บ๐ต๐ฉ๐ฐ๐ฏ3 ๐ณ๐ถ๐ฏ.๐ฑ๐บ ausfรผhren, kurz warten und los geht’s.
๐๐๐ซ ๐ฉ๐ฅ๐๐ง๐ญ ๐ณ๐ฎ๐ฆ ๐๐๐ ๐ณ๐ฎ ๐๐๐ก๐ซ๐๐ง? ๐๐ง ๐ฐ๐๐ฅ๐๐ก๐๐ง ๐๐๐ ๐๐ง?
An die Organisatoren des @ESE: Falls ihr etwas vom Design รผbernehmen wollt โ gern, die GPLv3 macht es mรถglich.
Video (nicht sichtbar in Vorschau)
Token usage
Friday, I analyzed how many tokens I use. I knew it was a lot. Also more than anyone in my bubble, I was sure of that. But I had never
measured it beyond the built-in โusageโ charts you get from some agentic harnesses.
Just to get this clear from the start: I donโt see it as some kind of merit to burn tokens and then brag about it. For me, this is on the same level as buying a luxury car, that bragging part. And i could also tell you how easy it is to misguide a “huge amount of tokens used”-metric. So believe me, all I invested, was for a good purpose.
In the past three years, I got a lot of things done that would not have been possible without generative AI. I grew and explored
lots of new ideas. AI served as ๐๐ง๐๐๐ฅ๐๐ซ and ๐๐๐๐๐ฅ๐๐ซ๐๐ญ๐จ๐ซ.
So, letโs look at the numbers: somehow, each month, my token usage grows ๐๐ฑ๐ฉ๐จ๐ง๐๐ง๐ญ๐ข๐๐ฅ๐ฅ๐ฒ. Just by a power of two. But two is
still powerful. Since my usage is split between severval computers and I donโt (yet) use a central portal that collects all the data, I focused on the main machine.
Tokens altogether for the price of ~$3,000 in August 2026. And that month is not over yet. Check the attached chart.
The growth in usage (for me) is easily explained with a historical analogy:
๐ฌ๐๐๐๐๐ ๐๐๐ ๐๐๐๐๐ ๐๐๐, ๐๐๐๐๐๐๐ ๐พ๐๐๐๐๐๐ ๐ต๐๐๐๐๐ ๐๐๐๐๐๐๐๐ ๐๐๐๐ ๐๐๐๐ ๐๐๐๐๐๐๐๐๐ ๐๐๐๐๐ ๐๐๐๐๐๐๐ ๐๐๐ ๐๐๐ ๐๐๐๐๐๐ ๐๐๐ ๐๐๐๐๐๐๐ ๐๐๐๐๐๐๐๐๐๐๐ ๐๐ ๐๐๐๐.
๐ฐ๐๐๐ ๐๐๐๐๐๐๐ ๐๐๐๐๐๐ ๐๐๐๐ ๐๐๐๐ ๐๐๐ ๐๐๐ ๐๐๐๐ ๐๐๐๐๐๐ ๐๐ ๐๐๐๐โ๐๐๐ ๐๐๐๐๐๐๐ ๐๐๐ ๐๐๐๐๐๐๐๐ ๐๐๐๐๐๐ ๐๐๐๐๐๐๐ ๐๐๐ ๐๐๐๐ ๐๐๐๐๐๐, ๐๐๐๐๐๐ ๐๐๐๐ ๐๐๐๐
๐๐๐๐๐๐๐๐ ๐๐๐ ๐๐๐๐ ๐๐๐๐๐๐.
๐พ๐ ๐๐๐๐๐ ๐๐๐๐ ๐๐๐๐๐๐๐๐๐๐๐ ๐๐๐๐๐๐๐๐๐.
What are you getting done with the help of agentic support?
Good news: ๐๐๐๐ YAML translations with ๐๐ฎ๐ญ๐๐๐ข๐ง๐ ๐จ๐๐ฑ๐ฉ๐ซ๐๐ฌ๐ฌ ๐.๐.๐
Since #Qt is not the only champion in the embedded domain, I’ve expanded the supported frameworks by making it possible to run it on the #i18n files from #LVGL as well. Maybe it is handy for someone else too ๐
The new mode is invoked with --lvgl-yaml, and you have to do it explicitly. The existing usage for TS files remains unchanged.
The source YAML files also stay untouched, so the result is written to a file named for each output language.
In the background, I also did some other plumbing, which had been on the list for a while: GitHub Actions now also cover the dependency graph, neat badges showing the pipeline states in the README.md, updated dependencies, and some quality hardening. So we have 58 automated tests now, 100% statement coverage, and Pylint reports 10/10.
That polishing and the above-mentioned feature are the result of continuous market review and constant adaptation. New competitors and technical standards emerge; as developers, we should be ready to embrace change and adapt.
Give me feedback if some other translation files need coverage as well.
Link to to the repo:ย https://github.com/marcelpetrick/CuteLingoExpress
๐๐ง๐ฅ๐ฒ ๐% of my ๐ฉ๐ซ๐จ๐ฆ๐ฉ๐ญ๐ฌ contain ๐ฉ๐ซ๐จ๐๐๐ง๐ข๐ญ๐ฒ
Testing Muse Glimmer lead to some frustration, so I started the next prompt with something I wouldn’t write professionally.
And this led to the question: how often do I do this? I would have guessed that 10% of my machine-human interactions contain some swear words.
But why guess when you can evaluate the data and produce hard facts?
Therefore I prepared ๐ซ ๐๐ ๐๐ง๐ญ๐ข๐ ๐๐ฐ๐๐๐ซ ๐๐๐ซ as project on GitHub, which evaluates both your ๐๐จ๐๐๐ฑ and ๐๐ฅ๐๐ฎ๐๐ ๐๐จ๐๐ logs and gives you on the CLI a short two liner. And additionally you receive an HTML page in nice green IBM 3279-style. All locally, no AI or models involved, just some Python and HTML.
It will reveal to you how many swearwords were used, their frequency, streaks without swearing, which hour of the day the tension rises high, etc ..
What do you think? Anyone has a higher score to offer? Leave me a comment.
GitHub: https://github.com/marcelpetrick/AgenticSwearJar
PDF with full feature view:
Screenshot:
3/x: ๐๐ซ๐จ๐๐ข๐ง๐ ๐จ: pipelines
In a feature-driven world, support-software rarely gets the stage it deserves. Ask a stakeholder what a pipeline is and get ๐ .. which is sad. Because how else do you want to verify it you built it correctly?
Anyway: automated testing and linting is always part of my process. From day one – not in the final stages. Of course, you should have at least a tiny build-able fragment of your project, but the earlier you add #automation, the better. I usually run with local and continuous integration pipelines.
This project is hosted on GitHub, so I went with GitHub actions for the CI. We have 20 named pipeline stages which form a single commit gate. “Cheap” ones like linting and format checks run before the more “expensive” ones, which need a build. 129 automated tests are done, which cover 98% of the code. Together with the 30 unit and widget tests and a real-target integration suite we have fitting coverage. The local version runs as pre-commit hook, the GitHub one is also capable of doing the releases. And so far I made six public releases.
Also, Dependabot is integrated, so if I would miss the release of any dependency, then this neat little bot would create an automatic PR (pull-request) for me. ๐ฆโโฌ
The pipeline turns engineering expectations into executable policy. ๐๐ญ ๐ฐ๐จ๐ง’๐ญ ๐๐ฎ๐ข๐ฅ๐ ๐จ๐ซ ๐ฉ๐๐ฌ๐ฌ, ๐ฒ๐จ๐ฎ ๐๐๐ง’๐ญ ๐ซ๐๐ฅ๐๐๐ฌ๐. ๐๐ข๐ฆ๐ฉ๐ฅ๐ ๐๐ฌ ๐ญ๐ก๐๐ญ.
If you want to give this Croatian-German-language learning app a try, download the package from https://github.com/marcelpetrick/CroLingo/releases/tag/v0.0.63 and run it on your Android phone.
Have fun and enjoy learning!
I’ll keep you updated on what comes next. ๐ญ๐ท โค๏ธ ๐ฉ๐ช
#continuousIntegration #continuousDeployment #pipelines #automation
2/x: ๐๐ซ๐จ๐๐ข๐ง๐ ๐จ
As written, I had started to gather all ideas and document what we want. Of course, there exist magic tools which transform unstructured input into well-defined #requirements and which help you to make them conflict-free, unambiguous, atomic, feasible and verifiable. Yada yada, you know the drill.
Then the development started, and we have a first #MVP (minimum viable product) now, as an Android release package and Linux Desktop build. The first content has been added, so the first user feedback could be gathered today. I have to admit, offering an app with well-known competitors yields a lot of “oh, but here it should behave like this” … anyway, input from the target audience is really dear to me. So we now have plenty more things to implement and some to adjust. But we did not experience a single crash or logic deadlock.
โจ ๐๐ง๐ ๐ฌ๐จ๐ฆ๐ ๐ฎ๐ฌ๐๐ซ๐ฌ ๐๐จ๐ฎ๐ฅ๐ ๐๐ฅ๐ซ๐๐๐๐ฒ ๐ฅ๐๐๐ซ๐ง ๐ฌ๐จ๐ฆ๐ ๐ง๐๐ฐ ๐ฐ๐จ๐ซ๐๐ฌ. โจ
I’ve added on-device screenshots from one of the recent builds. If you want the hands-on experience, go to https://github.com/marcelpetrick/CroLingo/releases/tag/v0.0.40
I’ll keep you updated on what comes next. ๐ญ๐ท โค๏ธ ๐ฉ๐ช
๐ฆ Release: ๐๐ฅ๐ฅ๐๐ฆ๐๐ ๐๐ซ๐ฆ โจ
Recently I had the need to monitor all the locally available #Ollama instances. Of course, you can ๐ค๐ถ๐ณ๐ญ yourself, but why not have a tool in the history of btop/abtop ..
Only one ๐ด๐ฉ๐ฆ๐ญ๐ญ script utilizing ๐ค๐ถ๐ณ๐ญ, ๐ข๐ธ๐ฌ and ๐ซ๐ฒ. The name is the architecture: one llama is a pet, several across machines is a farm.
Tons of hotkeys to change update frequency, re-discovery of servers, probing their VRAM, cycling color themes. GitHub Actions ensure high quality code.
So give it a try and/or write a better version, #GPLv3 allows it: https://github.com/marcelpetrick/ollamaFarm/
Ollama Farmer out ๐ง๐ปโ๐พ๐ฆ
New project: ๐๐ซ๐จ๐๐ข๐ง๐ ๐จ ๐ญ๐ท๐ฉ๐ช
Just wanted to share that I started the design and implementation of an app for learning Croatian.
The market for language-learning apps does not offer the combination I need, so it is time to roll our own custom software.
Also a playground for #Flutter and #Dart, since I have so far only used Kotlin for Android apps. And it will run on x86_64 Linux desktops as well. Maybe I’ll do an iOS version too.
Most of the preliminary work was spent on the design and concept. #Ideation is quite important in the age of agentic AI.
Of course, I will avoid writing code and keep you updated ๐
Final evaluation
The World Cup is over โ actually for quite a while, but I never had the time to do the final evaluation. Outcome was fifth place (yes, from second to fifth), because those two missing entries really made me leave 7-9 points on the table (on average), which could have yielded a second or third place.
I will re-invest the gained 18โฌ into pizza for the team and use it for some discussions about morality (is agentic resolution allowed for such games?).
And I won: my initial goal of fetching back my investment of the starter fee was met. Good.
And I learnt how to orchestrate agents to solve non-SW-development tasks.
#agenticAI