DeepSeek V4 pro max whatever gotta be the most dogshit model I've used in a while. Every prompt I write it will "but wait, <>" and generate the most horrendous code I've ever seen.
How the hell is this even possible in the big 26.
@REALnoble2024@nyaraVT To be fair, rightwing diversity spans from one guy who thinks the government bans raw milk to inject trackers, to another guy who wants the government to track literally everything. Sort of shit I see on RW twitter makes me believe that.
@localhost_5173 JS-based lsps are the bane of society. Even worse, if you were to use github copilot for AI itll spawn 3 processes that take 150-200mb each.
I made a simple website so you can snap pics with your plushie if you forgot to bring it or even if you're too shy to bring them out!
https://t.co/secdPTN3zW
@mehrdadisaloo@OutofGalaxyy Yeah the new core ultra and hx chips live 5-6 hours compared to the 2-3 that used to be the norm. Meanwhile macbooks even back from 2021 can go for 1-1.5 days.
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.