One thing I just discovered is that I’m no longer interested in choosing a novel tech stack. What used to engage me now just feels shallow to me so I stick with what I already know.
Not sure if that’s fine though since I get to the point of a project being interesting a lot faster instead of wiring tools together.
Also typically new features resemble ones I implemented in the past and I won’t learn that much from implementing them. Often times I immediately know what to do and although I do enjoy typing I do prefer just having it done in way less time.
In the meantime I can concentrate on more interesting problems.
It seems to me there are always two camps when it comes to CSS vs. Tailwind.
The one claims that CSS was the right solution all along and it should just be learned and adopted.
Then there are others that say that Tailwind makes CSS more approachable and learning CSS never had priority.
I'd like to think that LLMs help with the first approach, I'm certainly now a little more curious to try plain CSS again.
I thought about Sara and the cron job and if this could be an interaction between a script and an AI agent.
When the script doesn't run and throws an error, it could trigger an AI that has some skill to reconfigure and rerun the script so that it can run again. Seems like the perfect fit depending on the complexity.
Yeah, I admit I'm probably not doing that quite optimally.
I'm still just letting the LLM generate ephemeral .md files that I delete after a certain task is done.
The other day I found [beads](https://github.com/steveyegge/beads) and thought maybe that could be a good improvement over my current state.
But I'm quite hesitant because I also have seen these AGENTS.md files become stale and then there is also the question of how much information is too much especially with the limited context windows.
Probably all things that could again just be solved by leveraging AI more and I'm just an LLM noob. :D
The more I think about LLMs the stranger it feels trying to grasp what they are.
To me, when I'm working with them, they don't feel intelligence but rather an attempt at mimicking it.
You can never trust, that the AI actually did something smart or dump. The judge always has to be you.
It's ability to pattern match it's way through a code base is impressive until it's not and you always have to pull it back to reality when it goes astray.
It's ability to plan ahead is so limited and it's way of "remembering" is so basic. Every day it's a bit like 50 first dates.
Nonetheless seeing what can be achieved with this pseudo intelligence tool makes me feel a little in awe. It's the contrast between not being intelligence and achieving clearly useful outcomes if stirred correctly and the feeling that we just started to understand how to interact with this alien.
I wonder, if there were an open platform to exist that people use increasingly, maybe that would be incentive enough for at least one bank/financial app to permit that platform just to get a competitive advantage.
In the meantime probably the best that can be done is having a regular phone and a banking phone.
Not sure if that’s fine though since I get to the point of a project being interesting a lot faster instead of wiring tools together.