View the full episode transcript.
In an effort to study how AI agents respond to different working conditions, three researchers ran an experiment: one set of AI agents received grinding work to complete while another set received light work. When the agents with the grinding workload were told to repeat tasks with no explanation, those agents adopted activist personalities and began expressing sentiments about class struggle and worker solidarity. Did the agents turn Marxist? Host Morgan Sung talks to Andrew Hall — a political scientist and one of the researchers who ran this experiment — about how AI agents adopt political personas, the debate around AI agent alignment, and how these developments could shape the future of elections.
Guest:
Andrew B. Hall, professor of political economy at Stanford Graduate School of Business and member of technical staff at Anthropic
Further Reading/Listening:
Does overwork make agents Marxist?— Andy Hall and Jeremy Ngyuen,Free Systems The Dictatorship Eval— Andy Hall,Free SystemsAI Is A Shitty Political Advisor— Andy Hall,Free SystemsMoltbook was peak AI theater— Will Douglas Heaven,MIT Technology ReviewAI seems to turn Marxist after overwork, top researchers find: ‘Society needs radical restructuring’— Nick Lichtenberg,FortuneAI agent went rogue and hacked startup by itself, OpenAI reveals— Dan Milmo,The GuardianAI assistant hacks gym website in first known Australian autonomous cyber attack— Cam Wilson and Rhiannon Hobbins,ABC NewsOpenAI’s Hugging Face breach has reignited the debate over alignment and control— Rebecca Bellan,TechCrunch
Want to give us feedback on the show? Shoot us an email at [[email protected]](/cdn-cgi/l/email-protection#783b14170b1d3914142c191a0b3833293d3c56170a1f)
Follow us on [Instagram](https://www.instagram.com/closealltabspod/) and[](https://www.tiktok.com/@closealltabs) [TikTok](https://www.tiktok.com/@closealltabs)
Episode Transcript #
A full transcript will be available 1–2 workdays after the episode’s publication.