will to code

Today I'm gonna build an audiobook generator. #friday

compression != intelligence AI === AGI

It's funny Every single successful person only had to be right just that one time. After that one time the past failures didn't matter and the future was set in stone We only talk about their one time

If I can't see or feel it, then it must be some kind of lie

just look at that agency

Arguing with auto complete 🙄

It's such a shame that nobody is thinking in the 10 year time frame Were are the parc vibes???? There has never been this much money.... but the timeframe is so small that nothing revolutionary ever gets built Think in that timeframe create an organization centered around the idea that a group of people will be tasked with bringing something new to the world in 10 years time!

I tried opus, it did what I asked but not without turning the codebase into homework for me to study This is my new benchmark for AI:

Is it better at the task than me with a gun to my head

If the answer is no then just implement it yourself And don't ask it to implement things you don't understand yet, take the time to understand them and once you do ask that question again

If I was in Highschool right now i would def vibecode valorant and play it over LAN with frens you can make it so epic... like every agent's power is scriptable... write lua scripts that give agents special powers...

My YouTube recap came in

Today I wanted to make something with gpui then I realized that I didn't understand it enough So I built a to-do list app Super basic super simple you can just look at the codebase and understand what gpui is all about I am sooooo bullish on this framework GitHub Also discovered this amazing library. Its the shadcn for gpui. gpui-components

Cloudflare is down again lol Someone should really build this: One click infra migration

#friday

New deepseek model gpt-5 and gemini-3.0 level performance while being 10x cheaper It cost them 600k upto a mill to go from 3.1 to 3.2 which rivals frontier models that were trained from scratch for 100s of million It's over And it will be even more over when deepseek trains a new foundation model. The current one is Deepseek V3 from late 2024.

Another cool model It's a GUI agent that can use a phone and follow instructions accurately 4B params but still outperforms larger SOTA models

AI is humanity's great project This is interesting from deepseek. They make one agent generate mathematical proofs and another agent grade it's reasoning. They completely ignore the answer. My mind is blown. AGI is solvable only through the game theory we introduce in to agentic systems

I'm so pissed off I can no longer continue watching this How is it fair to put a system that sees millions of moves ahead against a human whose brain has very limited compute Limit the search depth of these systems to human level and they'll crumble Humans are yet to be defeated We are the master species 🧠 It's so disappointing to see the general consensus among everyone being "computers have defeated humans" I despise this whole narrative and will never accept it because it's built on lies and distracts from real AGI benchmarks and goals.

In programming we often say be efficient don't repeat yourself but does nature share that same sentiment

TL;DR: Nature is efficient when it needs to be but it fundamentally cares more about survival than elegance survival comes first, efficiency only matters when it helps survival

ML is so beautiful man 🫠 It's where math and cs meet together and become art