Oğuzhan Çakmak retweeted
The end of human slop is near.
Ok so I did the TV hack thing…
What started as a very conservative exploration has led to a fully custom home launcher with layouts, backgrounds, material choices and lots of customisation available.
I no longer have to deal with Samsung Smart Hub nonsense.
It's already live and working but now in a massive refinement pass thats been running while I'm in meetings.
🚀
Replying to @KenneyNL
This is bullshit, Kenney. I’m the same tech tree following optimist who moved from C to C++, from 2D to 3D, and from closed source to open source. I run a company. I write code. I contribute to published papers. I’ve upped my expectations of AI. Up yours!
Oğuzhan Çakmak retweeted
people are starting to realize.
there *are* no moats left. the only true moat in existence was intelligence, and now that's out of the equation.
Oğuzhan Çakmak retweeted
Apple calls the iPad a computer.
So I built Linux for it.
I built LinPad OS - Linux for iPad.
- Desktop windows + a real terminal
- No jailbreak. No VM.
Free & open source (pre-release).
What is your iPad missing?
linpados.com
#Linux #iPad #OpenSource
If you are not using @bot, you are saving a lot of your precious time. It is early beta at this point
I was thinking last night about how multi-agent workflows always end up as an org chart. orchestrator on top, an inspector checking the work, workers underneath. We rebuilt middle management for LLMs
so what's the right government for agents? Democracy, oligarchy, or the open source model where one benevolent dictator decides what gets merged
Right now the data leans dictator. a google/mit paper tested this: when agents work in parallel with no boss, one agent's mistake gets amplified 17x by the time it reaches the final answer. add an orchestrator that checks their work and it drops to 4.4x. democracy doesn't do great either. Letting agents vote helps less than you'd expect, because they're all the same model with the same blind spots, and they tend to cave to the majority
What I can't figure out is whether we should be copying human org structures at all. Bureaucracy exists to solve human problems: people have limited attention and you can't trust everyone. Agents break in different ways. and there's a paper where they let an LLM design the multi-agent setup itself, test it, and keep iterating. Its designs beat the ones humans built by hand














