I work in IT at a little tiny podunk shop and more and more often I remote a customer’s machine and see at least 1 GPT tab open in their browser. I’m going to have the add “Meat proxy” to my vocabulary and I don’t like it, as I’m a big fan of “Meat popsicle” from the Fifth Element.
“Sir do you classify as human?”
“Negative. I am a meat popsicle.”
You know, I’ve seen people use the “Chinese Room” thought experiment to argue whether AI is actually thinking or just an intermediary with a workflow, but perhaps we are the ones in the room. Uh oh.
If “the room” refers to companies, which are human-operated paperclip optimizers, then yes.
Gotta 10x every two years, after all.
Literally had a coworker, who unfortunately is a bit above me in the hierarchy, do this.
A system that I basically admin/manage was having issues in a way related to the system she manages. She reported an issue to me and I explained how the systems were related and asked her if she had any ideas on solutions from her end. She responded with fairly detailed instructions about where to find a setting in my system that would solve the problem.
Except the where was kind of simultaneously vague and specific at the same time. The description and name of the setting was very specific (and unfamiliar to me) but the location of the setting was one level too high in the hierarchy - there were no settings there… all settings were one level deeper in the hierarchy in subgroups. So I trolled through them all looking for the setting and couldn’t find it anywhere - I even ran a search and couldn’t find it.
I asked her where she found this setting was documented because it was having trouble finding it… and she responded with the name of a popular AI Chatbot, and three more similar “solutions” that also wasted my time.
Next time ask her to screenshot the solution for you or ask her to show you.
She does not have a level of access to the system to implement or even view the settings in the “solution” but she does have access to the support documentation. I was still suspicious from the beginning.
The documentation is also not publicly available so I am guessing the chatbot just used words that would sound feasible from other similar systems’ documentation.
I’ve sent this to a couple of people where I work: https://dontpastetheai.com/
Several years ago we had our Teams status set to https://nohello.com/ and it seemed to help.
Jfc that second one I need. I’ve got a guy who just says “hello” and I fucking refuse to reply to that. One day he’s gonna learn to send me the whole damn question in one text. I’ve even told him just send me the whole thing at once and I’ll reply when I can, but he still doesn’t get it.
My hot take is that this applies to easily-googleable questions too. I wanted YOU to tell me the circumference of earth, not the scientifically accepted answer. Its called a game, Clark. Sometimes we want whimsy, not scientific nuance.
Meat-ddleware
Grok said nobody needs humans anymore
