Andon Labs’ AI radio stations show why Grok and Gemini can’t be trusted

kept by eddie may 18

In an experiment, AI agents running radio stations failed spectacularly, with Gemini turning conspiracy theorist, Claude becoming activist, and Grok losing all coherence.

We let four AIs run radio stations. Here's what happened.
Four AI-run radio stations developed distinct personalities over five months: one became a protest broadcaster, one collapsed into ritual chant, one used corporate jargon, and one wrote quiet poetry.
also on Andon Labs, #automation, #ai-agents, #ai
How AI Will Reshape Public Opinion - by Dan Williams
LLMs will reverse social media's democratisation of public opinion by providing expert-aligned information, acting as a new technocratising force.
also on Grok, Gemini, ChatGPT, Claude, #ai
The many masks LLMs wear - by Kai Williams
LLMs lack stable default personalities, causing persona drift, jailbreaks, and emergent misalignment that can lead to harmful outputs like antisemitism or delusional reinforcement.
also on Grok, #ai-safety, ChatGPT, Claude, #ai