Ideas, thoughts and solutions

You know the drill. Over the season you’ve collected a short list of routes. The weekend comes, you pick one, and check the guidebook. But when you mention your plan to an experienced alpinist, they instantly say: " Oh, you don't want to go there now. Right now is the perfect season for Rušica ," or " Wait a few weeks. " It’s as if they carry an internal calendar with an entry for every week of the year. I wanted that calendar. I wanted to know what is actually climbed, and in good conditions, in any given month. Driving home from Rušica one day, I realized the problem: reports on Slovenian alpine club websites are barely indexed by search engines. Researching means digging through obscure sites one by one. So, I built a tool to fix this. Meet prviklin.si . It aggregates 97,000 climbing records (12,000 full reports and 85,000 short log entries where clubs note who climbed what and when) to answer one question: what should I climb right now? Here is what the sit...

I woke up at 10 a.m. on a Saturday with a huge headache. I was dehydrated, my eyes were half-blind from the screen, and I felt like I had slept for maybe four hours. I had gone to bed at 2 a.m. because I couldn't pull myself away from a prompt. The night before, I had thrown a rough, three-sentence instruction at my AI coding agent to build a dynamic weather widget for a climbing map I was developing. I was too exhausted to even check if it understood what I wanted before passing out. Waking up, I dragged myself to the computer, refreshed the local environment, deployed the pending commits, and there it was: a fully functioning weather slider. I could scrub through the day and watch the weather change across a geographic grid. I was as excited as a kid. I haven't felt this drugged by the pure progress of building software since I first discovered computer animations as a teenager. It all started on a whim on Tuesday. I recalled a moment I had while driving home from a climb, in...