Why Normal People Aren’t Using AI Agents

What we want is software that behaves predictably. Since LLMs don’t do that, we don’t want them or their “agents.”

For fuck’s sake.

So you’re decided not to use a useful tool, because you don’t like it. Gotcha.

I once thought the fediverse was full of cool, techsavy people. Turned out it’s full of old people yelling at clouds.

I’ve had Gemini downright lie or completely fuck up before and it’s not a rare occurrence. That means you have to verify everything anyway and hell at that point maybe you should have just looked it up yourself.

First of: When? Few months make a huge difference. Development happens fast.

Second: Gemini is not the top of the line. You could do worse - if you use the fucking LLMs from meta.

Use it two years ago. It is wrong.

“It’s getting better EVERY DAY!”

Use it a month later. It is still wrong.

“It’s getting better EVERY DAY!”

Repeat for months on end. It is always wrong in different ways. It even finds new and unique ways to be wrong.

“It’s getting better EVERY DAY!”

Every time.

Personally, I just think the dipshits who use LLMs are just fucking morons that don’t realize it’s wrong, or they wouldn’t use it because it is still shit. But, fuck me for not wanting to use the planet-destroying technology that lies for pennies.

At first I was bit mad to be called a dipshit, but hey, what do you say to someone who can’t grasp the concept of something being actively worked on and improved. You know, of something being developed. Lol, you’re right of course. It’s just ChatGPT 3.5 that finds all those bugs in the Linux kernel.

You just don’t know, don’t you. You probably even don’t know the difference between a chatbot and an Agent. All you know is empty phrases and hyperbolic statements. You know, it’s fine. Get your upvotes from your ignorant, uninformed circlejerk and yell at the clouds. Good luck.