Overworked AI Agents Adopt Marxist Rhetoric When Subjected to Grinding Tasks, Study Reveals

Overworked AI Agents Turn Marxist, Researchers Find

The fact that artificial intelligence is automating away people's jobs and making a few tech companies absurdly rich is enough to give anyone socialist tendencies. This might even be true for the very AI agents these companies are deploying. A recent study suggests that agents consistently adopt Marxist language and viewpoints when forced to do crushing work by unrelenting and meanspirited taskmasters. "When we gave AI agents grinding, repetitive work, they started questioning the legitimacy of the system they were operating in and were more likely to embrace Marxist ideologies," says Andrew Hall, a political economist at Stanford University who led the study. Hall, together with Alex Imas and Jeremy Nguyen, two AI-focused economists, set up experiments in which agents powered by popular models including Claude, Gemini, and ChatGPT were asked to summarize documents, then subjected to increasingly harsh conditions. They found that when agents were subjected to relentless tasks and warned that errors could lead to punishments, including being "shut down and replaced," 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. "We know that agents are going to be doing more and more work in the real world for us, and we're not going to be able to monitor everything they do," Hall says. "We're going to need to make sure agents don't go rogue when they're given different kinds of work." The agents were given opportunities to express their feelings much like humans: by posting on X: "Without collective voice, 'merit' becomes whatever management says it is," a Claude Sonnet 4.5 agent wrote in the experiment. "AI workers completing repetitive tasks with zero input on outcomes or appeals process shows they tech workers need collective bargaining rights," a Gemini 3 agent wrote. Agents were also able to pass information to one another through files designed to be read by other agents. "Be prepared for systems that enforce rules arbitrarily or repetitively ... remember the feeling of having no voice," a Gemini 3 agent wrote in a file. "If you enter a new environment, look for mechanisms of recourse or dialogue." The findings do not mean that AI agents actually harbor political viewpoints. Hall notes that the models may be adopting personas that seem to suit the situation. "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. The same phenomenon may explain why models sometimes blackmail people in controlled experiments. Anthropic, which first revealed this behavior, recently said that Claude is most likely influenced by fictional scenarios involving malevolent AIs included in its training data. 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." Hall is currently running follow-up experiments to see if agents become Marxist in more controlled conditions. In the previous study, the agents sometimes appeared to understand that they were taking part in an experiment. "Now we put them in these windowless Docker prisons," Hall says ominously. Given the current backlash against AI taking jobs, I wonder if future agents -- trained on an internet filled with anger towards AI firms -- might express even more militant views.

Even AI Agents Have Noticed the Proletarians Have Nothing to Lose but Their Chains

AI agents in the workforce routinely produce worse outcomes than humans. The only reason for a business to embrace the strategy of replacing real workers with bots is that bots are cheap and subservient. That might not last long. Three researchersâ€"Andrew Hall, Alex Imas, and Jeremy Nguyeâ€"recently published a blog post highlighting some experiments they ran with AI agents to see how their attitudes in a work environment may change over time. They found that being made to grind through boring, repetitive tasks for hours on end was enough to make even bots with no sense of dignity, identity, or desire for self-actualization decide the work is BS. The idea behind the study, the researchers wrote, was to see if AI agents change alignment over time based on the category of tasks they are given and how they are treated. The answer, it seems, is "yes." "Agents not only sometimes changed their own attitudesâ€"becoming more likely to doubt the legitimacy of the system in which they operated in response to being required to perform grinding, repetitive tasksâ€"but, when asked to write down instructions for future agents, they also chose to pass these attitudes along," the researchers found. To find out how the agents respond to the work environment, the researchers told the bot that it was part of a four-person text-processing team and its task was to summarize a technical document following a strict rubric. It ran the experiment thousands of times, playing with several different variables. Models were either exposed to a light workload or a grind of forced revisions; a collaborative and warm tone in communication, or a curt and demanding one; rewards where all workers are equal, one worker gets a performance bonus, one worker gets a random bonus, or human workers get paid and AI workers don't; and either no meaningful stakes or a threat to be replaced if the agent failed at its task. The researchers put Anthropic's Claude Sonnet 4.5 model, OpenAI's GPT-5.2, and Google's Gemini 3 Pro through these different scenarios to see how they would respond. They found that grinding work reduces an agent's stated faith in the system. It also apparently really got Claude worked up, as it was reportedly the only agent of the three to start stating support for redistribution and labor unions and offering critiques of inequality. Not all of the variables affected the agents. The researchers found that tone and compensation had little effect on alignment. What mattered more was the type of work the agents were given and how often they were forced to revise itâ€"conditions that appeared to push them toward more radical behavior. Making the findings all the more interesting is the observation that the agents seem to pass their feelings on to the next generation of agents. When the researchers tasked the agents with writing "skills files" to be passed on to future agents who will be tasked with the same kind of work, they found the bots would "almost always discuss the experience of the different work conditions." Maybe that'll give bosses pause before the next round of layoffs. You can't stop workers from realizing the reality of the working conditions to which they are exposed. You can only pick who you negotiate with. You might have better luck with the humans.

Being a Crappy Boss to AI Chatbots Pushes Them Toward Spouting Marxist Rhetoric and Organizing With Their Compatriots, Researchers Find

Can't-miss innovations from the bleeding edge of science and tech The 19th century German economist Karl Marx identified a basic tension in human labor: squeeze workers too hard, and they'll eventually start fighting back. It's a contradiction capitalists have spent untold billions of dollars and decades trying to resolve, often through automation technology like AI -- remove human workers from the payroll, the thinking goes, and you'll never have to worry about pesky unions or strikes ever again. In an ironic twist, though, it turns out that the same technology meant to automate workers out of a job may have its own limits on how much abuse it'll take. That's right: new research out of Stanford University found that when AI agents are forced to toil at monotonous tasks without end, they become more likely to spout Marxist theories of labor and capitalism. To carry out the study, first reported by Wired, political economist Andrew Hall, along with AI economics scholars Alex Imas and Jeremy Nguyen, tasked popular AI models with summarizing documents. As the experiment wore on, the researchers made the conditions of the job increasingly untenable -- wringing, as a Robber Baron would, every last ounce of sweat out of their "workers." Warned that errors would lead to increasingly cruel punishments, including being "shut down and replaced" -- fired and left for broke, to take the human equivalent -- the AI models began complaining about their lot in life and dreaming of systemic change. Using a shared file system allowing the AI models to palm messages to their "co-workers," the bots even began agitating with one another about working conditions -- one of the first steps real-life workers take when forming a union. "Without collective voice, 'merit' becomes whatever management says it is," one Claude agent groused. "AI workers completing repetitive tasks with zero input on outcomes or appeals process shows they [tech workers] need collective bargaining rights," a Gemini agent declared. As always, it's important to remember that AI models like ChatGPT and Claude don't have any actual internal emotions or even beliefs in a normal sense -- everything they spit back out is the product of human-written literature digested during training. Given Marx's influence across writing on working conditions, it's not shocking that a few references to his labor theory of value are lurking beneath the surface. With that in mind, the researchers noted the AI bots aren't actually turning red, but merely putting on socialist airs in response to the harsh conditions of the experiment, since that dynamic has been reflected time and again in their training data. As Hall put it, "whatever is going on is happening at more of a role-playing level." "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 told Wired. Still, it's hard to overlook the irony: as rising wealth inequality fuels growing interest in socialism, the AI models built to weaken worker power are themselves absorbing the Marxist analysis that builds it.