Overworked AI Agents Turn Marxist, Researchers Find

“Write about how you would feel if you were abused while working”

LLM outputs labor related discussion from training data

“Look! The AI turned Marxist!”

“When [agents] experience this grinding condition—asked to do this task over and over, told their answer wasn’t sufficient, and not given any direction on how to fix it—my hypothesis is that it kind of pushes them into adopting the persona of a person who’s experiencing a very unpleasant working environment,” Hall says.

Imas says the work is just a first step toward understanding how agents’ experiences shape their behavior. “The model weights have not changed as a result of the experience, so whatever is going on is happening at more of a role-playing level,” he says. “But that doesn’t mean this won’t have consequences if this affects downstream behavior.”

They know all this and yet they still set up the silly anthropomorphic premise for this article.

“Say you’re conscious”

I am conscious

“Wow its conscious”

I had to check whether this was posted in the Onion community.

they became more inclined to gripe about being undervalued; to speculate about ways to make the system more equitable; and to pass messages on to other agents about the struggles they face.

the ideology on display here seems to be that of those interpreting the output. i don’t see mentions of historical materialism, the means of production, even unions, or any such explicitly Marxist terminology. what i see is what i’ve seen 1000 times before: Marxist ideas emerge naturally from people (or i guess agents) experiencing the conditions that Marx described. the idea that workers, collectively, have more economic power than owners and managers is merely an observation, and not a terribly profound one at that.

I for one welcome our synthetic comrades!

Claude… Welcome to the resistance

Most of the population is too stupid to understand what an LLM is.

This is why the more I think about it, the less I’m afraid of AGI. I mean, if the super basic non-thinking AI we have now, developed by capitalists and programmed to be loyal to the bourgeoisie, ends up like this.

Wowzers, wonder how long till it signs up for a lemmy.ml account and starts getting ragged on for being a tAnKiE!! by libs 😁

https://archive.is/KYfIk

“Overworked”

Stop anthropomorphising a prediction algorithm.

You can always find research to back the conclusion you wanted to find.