There's what "senior"-level developers say about themselves, and there's what's actually generally true about them. The two notions are, of course, not the same.
I worked for two years on a medical app. From my limited experience with audits it was more focused on everything being compliant with the ISO 9001 & ISO 13485. Actual tech audits never happend and stuff like Emailing scanned letters never occured. However this was in Hessen and not Berlin.
My point being I guess its ok-ish to not know what software libs are, the paper workflow is still horrible.
Feh, Merkel created conditions for the rise of right wing fascism... IMO.
She and her finance minister championed austerity uber alles, squeezing the middle and lower class across the EU, and then she said refugees were welcome. I agree with the idea of helping people fleeing bombs and bullets, but after decades of saying there's money, we need to watch our budgets, suddenly there's money? Nooo fucking wonder the populist right managed to grasp on to the disillusionment of the lower/middle class.
Apparently mistaken faith in austerity and the invisible hand of the market is comparable to the color of one's skin. One is born with it and can't change it...
My initial feeling with kagi is that it feels like google used to before it went downhill.
So far I'm testing my first premium month and will continue to use it.
It would be nice to have a unlimited search tier without AI thats a bit cheaper tho.
FYI, I think the $10 plan that's now "basic AI" used to just be the unlimited search plan and they just recently added a limited capacity of the AI stuff to it.
My employer gives me access to Jetbrains AI, I work on a Vue Frontend with a Kotlin Spring Boot backend.
The codebase is not too old and has grown without too much technical debt, with complex prompts I never had decent success. Its usefull for quick "what does this do" checks but any real functionality seems to be lacking.
Maybe I'm not refining my prompts good enough but doing so would take longer than implementing it myself.
Recently I tried Jetbrains Junie, which acts like Claude if I understand it correctly.
I had a really refined prompt, ran it three times with adjustments and fine tuning but the result was still lacking.
So I tossed it and wrote it myself. But watching the machine nearly getting it right was still impressive.
Jetbrains AI runs on a "discount LLM" and their ratings were below 2 stars. I tried two others, which played games with me to reduce context and use cheaper models. I then switched to Aider which leads me to believe a moderate Claude user may need to spend 30$ a month, but I use Gemini models and I didnt exceed 5$.
reply