Tech, life and everything else
Regarding my last post: While I spent plenty of thoughts on the whole implementation, most of the coding work was actually done by DeepSeek V4 Flash and Pro, and I just supervised and criticized it.
If you are searching for a European OpenRouter alternative that also supports audio transcriptions, cortects might be an alternative. Given the recent controversial developments at OpenAI, and as I was already on the search for European alternatives, I deleted my OpenAI account and switched to Cortects for the few places where I need an AI API. The UI and feature set still aren’t as polished as OpenRouter, but at least it has the audio transcription endpoint, which I use for a voice-to-text Telegram bot. For now, I mostly use the Mistral models.
While you can spend endless money on AI coding tools, I’m known for being a money-saver (I even secured the sparzauberer.de domain, which is translatable to savings wizard).
For our wedding, I planned to develop a small site where guests can get more information, confirm their attendance, and view and upload photos. I started the base for that website in August and also bought a domain a few months ago. But I didn’t finish the coding. The design shouldn’t be as simple as my blog’s design, and I chose Angular for the frontend, as I also wanted to strengthen my Angular skills for professional reasons. Later, I wanted to build the backend using some n8n workflows.
Somehow1 I got access to GitHub Education again, which includes access to GitHub Copilot Pro. While I was using Kilo Code with OpenRouter in the recent past, I wanted to try Copilot again since it doesn’t cost anything extra for me.
I finally took a closer look at OpenRouter today, added some credits, and used it with the Kilo Code VS Code extension to vibe code (or at least guide the LLM to code) a bit on the wedding website I’m building for next year. I used the Grok Code Fast 1 model most of the time. Furthermore, I also switched this blog’s AI plugins to use Mistral Small 3.2 for summary generation and image caption generation.
I wish there would be a European alternative that is as simple and supports as many models as OpenRouter. Ideally, it would even support the audio transcription endpoint with models besides Whisper.
And I need to experiment with some other models for coding, as I don’t like it being from one of Elon’s companies. At work, I use GitHub Copilot with Claude Sonnet 4 or 4.5 most of the time.
But the AI world is moving fast; I guess it’s just a matter of time.
I previously shared my transition from Komoot to OsmAnd, and after some time, I’ve grown accustomed to its comprehensive capabilities. Whether for cycling, hiking, or general navigation, OsmAnd truly functions as a versatile “Swiss Army knife” for offline mobile navigation and tracking.
If you’re reading this, it seems that my GoBlog Telegram Bot (just another embedded plugin) is working!
This new bot probably has no real use, but it was a good experimental project to try and get a bit more familiar with the current state of GitHub Copilot, especially as we can now use it at work.
Probably the biggest use is for uploading photos from my phone. I can just send them as files and get a link back. But I can also send text and it publishes it. Even with frontmatter to configure parameters for the post.
Regarding Copilot: For whatever reason (maybe my adblocking DNS?) the VSCode extension keeps asking me to log in again, but still works for the non-chat features.
However, I am still a little worried that AI will make my work obsolete.
I tried GitHub Copilot (Free) in Visual Studio Code again for some small GoBlog changes. Copilot can now generate tests (although it doesn’t feel intelligent, as you need to correct quite a few things), it can do code reviews before committing and it can generate commit messages. Of course, it can also do code completions and write complete code, if you want it to do so.
To reduce my dependence on USA-based products, I switched from using the OpenAI API to Scaleway’s Generative API for my blog. Not only is it cheaper, but it’s based on open-source models, hosted in Europe. 🇪🇺
It was straightforward to just add an option to change the REST endpoint in my GoBlog plugins, and then use Scaleway’s API for creating the post summaries and the image descriptions. For the post summaries, I am now using llama-3.3-70b-instruct, for the image descriptions pixtral-12b-2409.
Let’s hope that there will also be a model that supports audio transcriptions until April 2026, so I don’t have to renew the credits on the OpenAI API for my Telegram Voice-To-Text bot. 🤞