On X
A selection of my posts on X as @Jera_Value.
461 posts
Worth noting, I started playing around with local LLMs for 2 reasons:
1. I’d burned through my Codex limits 2. Uncensored Qwen was available
We’re at a point where local AI can be really, really useful — and can complement tasks from the main providers.
Building mini-companies / side projects teaches you more than any course
It teaches you things related to engineering, marketing, and product. Things you could never learn as quickly any other way.
And on top of that, it does it well. In a lasting way.
Lessons learned the hard way stick better than ones explained on a whiteboard.
You're a first-year tech bro, right?
You just finished reading a Twitter thread by some guru who put together a demo in an afternoon. You watched a two-minute video where an agent opens the browser, searches for information, writes code, sends an email, and updates the CRM like…
Yeah, making over 100k a year is great.
My main goal when I came to Switzerland was to find a better life: to escape the lower middle class and find hope for a brighter future.
startup idea:
an app / website that lets you donate money to fund a specific person's IQ test.
did some retard insult you?
you chip in a measly €5 to see if he takes the test and finds out what his problem is
the money can only be spent on the test.
Also works for therapy sessions or other variations.
Altruism has never been so biting
Wait, does Claude's web app also use up the tokens in your plan?
WHAT. I hadn't used its web interface in years, and now I find out it's eating into my Fable usage.
OpenAI has a separate quota for its web interface. I thought Anthropic would do the same... in its defense, the web app has improved, but holy shit...
It was a good decision to make myself write a blog post every week for a few months.
And it was also a good decision to stop in time.
It helped me get started, find a rhythm and shape the blog.
A/B testing, like Bayesian thinking or sex, is one of those things you can’t go back from once you discover it.
I'm convinced that if I knew exactly what I needed to do, 3 hours of work a day would be enough.
But since I don't, I have to put in 8 to 12 hours.
The price of ignorance.
It's hard to get out of your bubble.
For example: in my circle of friends, cheating on exams wasn't normal. Neither was shoplifting. And especially not in high school. So I more or less tacitly assumed it wasn't common.
