@iraklidev@jeffrey_way The result was that I asked if it was stupid because it was completely off track. So no. I don't trust it to build anything beyond basic, crappy applications. And who's to say that it doesn't start to fool people the more "intelligent" it gets.
@iraklidev@jeffrey_way The AI delivered the use cases with a title and a short description. Two messages later, I asked it to create more detailed use cases for the first five, which were listed in the previous message.
->
If someone had told me ten years ago that ten years later I would be arguing with a stupid AI, I would have told them to go fuck themselves. But here I am. I am pissed off by its condescending tone and made-up nonsense. 😂
I ett samtal om 20 år:
Någon: vad skulle du säga är din största idé?
Jag: Att jag var som alla andra… till och med lite sämre än alla andra. Så, min största idé var att jag var en osann föreställning om mig själv.
I just came off of a flight from San Francisco to New York.
Midway through the flight one of the engines started to fail due some unknown technical issues.
The pilot was preparing us for an emergency landing in Gary, Indiana.
I pulled out my maxed out MacBook Pro M4, fired up Claude Code, connected to Opus 4.5, and instructed it to sniff out the ports on the internal airplane communication network.
In less than a minute it had full access to all the critical systems.
I instructed it to diagnose the problem with the engine and find a fix.
It reasoned for a few minutes, coded a simple firmware patch update for the engine, and uploaded it to the airplane mainframe.
Before too long the captain was announcing that all the engine issues have been resolved and we will continue on our journey.
We are definitely in the hard takeoff. Like literally.
you know how sometimes you read text and it just stinks of ai?
wikipedia has a great list of tells: https://t.co/V6CiJXuW9j
i thought it'd be fun to put all of it into a system prompt to avoid having text sound AI generated - it works pretty well.
prompt in the reply below:
Någonting jag aldrig trott att jag skulle säga är: lita aldrig på det AI säger.
Ibland är det som att prata med en övertygad treåring och denne är helt övertygad om att det denne säger är 100% sant.
Det mest störda är att när jag vet att den har fel och den inte ger sig… 🖕