@elonmusk Friends and family don't believe me when I say this. I now have a strong hope in isolated independent YouTube journalists who show real pictures of a hidden world.
Spending at AI DevCon, a lot of great talks. Really enjoyed the @patrickdebois one, from agents to org, good practices and so on. https://t.co/4O5fbskXJT
It’s two minutes to midnight. The time for talking is over; the time for action is now. That’s why we are presenting the first-ever patriotic European Citizens’ Initiative: the @SaveEuropeAct.
Acknowledging the ethnocultural continuity of Europe’s peoples as crucial for the preservation of Europe, we demand an immediate and total halt to immigration and the creation of a comprehensive European Remigration system.
To achieve that, we need your help. With a million signatures, the European Commission must meet with us face-to-face and take a stance on remigration and the future of Europe as a whole.
I've got an agent in a loop optimizing a renderer with the goal to minimize frame times (and tests to measure). It got times down from 88ms to 2ms and allocations down from ~150K to 500. Sounds good, right? Wrong. This is exactly why agent psychosis is a big fucking problem.
As an experiment, I rewrote the Ghostty core render state in Go, with access to identically laid out data structures as Ghostty and the exact same validation tests. I made a purposely naive renderer (simple, correct, but slow). 88ms per frame with 150,000 allocations (horrendous, lol)!
I then kickstarted a Ralph loop to bring the frame times down. I told it it can't modify input data structures or the public API or tests (they're correct), but it can do anything else it wants. It got to work.
It has worked for about 4 hours. I've spent around $350 on this experiment so far. The results?
88ms => 1.5ms
150K allocs => ~500 allocs
Incredible right? Nope.
My hand-written renderer I ported has frame times (same benchmark) of ~20us (0.020ms) and 0 allocations in the update path.
This is the problem with psychosis and lacking systems understanding. If you don't understand the system, you're going to accept that this is an incredible result. If you understand the system, you'll see better solutions immediately and can do roughly 75x better on throughput.
The people who blindly trust agent output are in the former camp. They're sheeple, overdrinking from a fountain of mediocrity.
Standard disclaimer: I use AI all the time. I like AI. The point I'm making is to not blindly accept results. Think. Analyze. Learn.
@RupertLowe10@ukhomeoffice Settled status here, I'm french and I love your country. Hard-worker and contributed for 21 years, bought a house, my son was born in England. I'd still be advocating for your party, as I believe English people are entitled to fight for their culture. Where does that leave me?
I'm binging videos on this channel, Matt and Julia are such lovely travellers. Such a positive attitude towards harsher part of the world. They show how amazing people can still be. The ones about Afghanistan are amazing. https://t.co/h8cTy7xoUB #travelling#Traveller
@Asmongold I don't know either of you, but I've heard him once on your stream, I could tell he was sounding very proud of you. I'm pretty sure he'd try to cheer you up and wait that you get up. My condolences.
@kreativeking That's what I'm currently doing but I was after a tool to centralize modules instead of having them on several repos (like https://t.co/6bTnL38ftr).