Posts in "AI"

The Certainty Trap

Superhuman AI poses risks that require informed engagement and responsible action at an individual level, rather than succumbing to paralysis or denial about its potential dangers.

I really like BMAD for planning my projects. Sure it is a really lengthy process. But it is super comprehensive and reveals a lot of areas I didn’t think through properly.

Still Possible

Creating project specifications can be more enjoyable than actual coding because it allows for an idealized vision free from the complexities and challenges of implementation.

I‘m back on OpenClaw

Last week I deleted the entire thing from my Raspberry Pi. This week I’m back with a fresh install and a simple, but important rule: Baby steps. Last week I got overwhelmed by the possibilities and tried to implement everything all at once. Not a good idea. So this time around I’m taking baby steps. I installed it. Made Telegram work and set up a text to speech and speech to text flow.

I’m struggling right now. I’m being pulled in too many directions at once. Unfortunately, my coping mechanism is to dive head deep into LLM coding and ignore everything else. I need to find a way out of that tunnel vision mentality.

I am finally back at coding my iOS app dialysisPal in a way the forced 5 months break was a godsend. The AI world has evolved quite a bit and it allowed me to give quite a bit of polish to the app’s UI/UX. It looks really nice now.

AI as in Addictive

The one thing that sucks about AI coding is that it is very addictive. I have a hard time letting go once I start. Features and bug fixes are done so fast that the urge to quickly do „one more“ is overwhelming for me. Just taking a peek how a the AI is doing easily turns into an hour or more of me sitting in front of the computer. And I have a hard time focusing on other tasks (housework, other projects, etc.