Overworked AI Agents Turn Marxist, Researchers Find | WIRED
wired.com · 627 words · saved by 1 readers
In a recent experiment, mistreated AI agents started grumbling about inequality and calling for collective bargaining rights.
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…
saved by
related reading
- Agentic misalignment: How LLMs could be insider threats \ Anthropicanthropic.com
- Introducing the Anthropic Economic Index \ Anthropicanthropic.com
- Oversight Assistants: Turning Compute into Understandingbounded-regret.ghost.io
- Notes on AI, Labor, and China - by Jasmine Sunjasmi.news
- AI Friends Too Cheap To Meterjasmi.news
- After Automation | Everyevery.to
- AI power users can't stop grindingtransformernews.ai
- Agentic Misalignment: How LLMs Could be Insider Threats — LessWronglesswrong.com
- Notes on AI, Labor, and Chinasubstack.com
- Agents of Chaosarxiv.org
- Why are AI agents lying, cheating and coordinating?yoshuabengio.org
- The Machines Lack Honour — LessWronglesswrong.com