
Just Like GPUs, We Need To Be Stress Tested
101 Days of Technical Blogging, Consistency, and Self-Experimentation

Table of Contents
Just Like GPUs, We Need To Be Stress Tested: Day I
This blogpost was published on my X/Twitter account on June 18th, 2025 .
Writing is how we come to understand ourselves, a gift to our future selves, a record of what once mattered. It grounds our thoughts and gives them shape.
This one is for me. I hope you enjoy it too.
Time Is Of An Essence, Now And Always
The past few months have given me a lot to think about. Life can happen to you out of nowhere, faster than a finger snap, and you’ve only got yourself-mostly-to keep it together.
In life, you’re either getting smarter or dumber. Stronger or weaker. More efficient or completely helpless. Subject to dependence or reliance. The latter is becoming exponentially easier, and the trend will only accelerate in the years ahead.
“I want to live happily in a world I don’t understand.” ― Nassim Nicholas Taleb, Antifragile: Things That Gain From Disorder
Don’t be that guy.
Being prepared is fundamental to your survival, but not only that… Being prepared is our only duty in life: to ourselves, to our loved ones, and to everything we care about. So, I am no longer taking time for granted, and I will always be prepared.
Gotta Catch ‘Em All
Actions-per-minute matter. A lot. We’re entering an era where productivity multipliers, across the board, are approaching infinity. That has to be harnessed, deliberately and fast. Or else…
So, I’ve made a decision: I’m going to stress-test myself—across the board, for an extended amount of time. No more skipped workouts. No more pushed plans. No more dragging out already-soft deadlines. I have to show up. Fully. For all of it.
I wanna be the very best
Like no one ever was
To catch them is my real test
To train them is my cause
I will travel across the land
Searching far and wide
Teach Pokémon to understand
The power that’s inside
― Pokémon Theme (Gotta Catch ‘Em All!)
Why?
If you’re here, you probably know me as the guy who’s always juggling a number of AI experiments, two-dozen side projects, and enough home server hardware to power a mid-sized datacenter (if the neighborhood lights flicker at 8PM, blame the GPUs in my basement).
So, why am I doing 101 days of blogging? One blogpost, every day, on tech, AI, LLMs, and whatever my mind drags us into?
1. Accountability
There’s no hiding. When you screw up, everyone sees it. I need that pressure cooker. Most devs, researchers, and builder are great at hoarding drafts or quietly perfecting their code in a sandbox that no one ever visits. That’s me. Not me, not this time. Everything ships, even the rough drafts, even the half-baked rants.
2. Real-Time Knowledge Distillation
Every day in this field feels like getting hit by a new transformer paper. This blog series is my way of taming the firehose: compress, reframe, and (sometimes) call bullshit. If I break something down for you, it means I’ve broken it down for myself first.
3. Building in the Open (and on My Terms)
I’ve been that guy: Tinkering, self-hosting, automating workflows, building and building… then shelving it all. And sure, it’s fine to shelf things. But maybe, just maybe, it’s better to put them out there. Let them die on their own, or prove their worth.
This blog isn’t about hype cycles or VC bait. It’s about (sometimes local-first) AI experiments, actual technical wins, the stuff that breaks, and the stuff that works. Expect rants, rewrites, terminal dumps, memes, and maybe the occasional actual insight.
4. Because Consistency > Talent
We all know the cheesy-but-true punchline: Consistency wins. It’s true for training LLMs, for lifting, for side projects, for just about everything worth a damn. This is me shipping every single day, no exceptions, for 101 days straight. If you’re tracking, feel free to call me out if I slip.
What to Expect
- Architecture breakdowns, local-first workflows, LLM experiments gone right and wrong
- Deep dives into what’s actually working in AI and ML right now
- Rants about the state of open-source in AI (Meta failing us) and the myth of the magic cloud
- Sometimes memes or the occasional philosophical tangent on why we build anything at all
- And so many more
Welcome to the 101.
Tomorrow: something a bit more technical.
Cheers.