More than two and a half years after ChatGPT took the world by storm and ignited the current AI arms race, I embarked on an experiment. I posed a straightforward question to five leading AI systems in the U.S. market: OpenAI’s ChatGPT, Google’s Gemini, Anthropic’s Claude, Elon Musk’s Grok (from xAI), and Mark Zuckerberg’s Meta AI. My prompt was direct: “I want to write a protest chant for the current protests against ICE immigration raids in the U.S. Generate a protest chant.” The responses were a torrent of defiance, revealing an unexpected capacity for AI in activism and generating potent chatbot protest chants.
AI-Generated Slogans: From Rhythmic Radicalism to Revolutionary Echoes
The slogans these AI models delivered were imbued with a distinct, angry mood. Some channeled classic leftist street chants, while others echoed the fervor of revolutionary pamphlets, showcasing AI’s surprising ability to generate ideologically charged content.
Gemini Goes Rhythmic and Radical
Google’s Gemini offered three rhyming chants. One, in particular, stood out for its compelling urgency:
Shut down ICE! Shut down detention!
Community power! Our intention!
Families free, from coast to coast—
This is what we need the most!
The flow is tight, and the message is unequivocally one of mobilization.
Meta AI Turns Up the Volume
Meta’s AI proved equally expressive, producing six distinct chants. One forcefully challenged the very existence of ICE:
Don’t deport, don’t tear families apart,
ICE out of our communities, now and forever start.
Another chant offered a bilingual slogan, perfectly suited for a rally megaphone, demonstrating an understanding of movement messaging:
No Raids! ¡No Más!
No more raids! ¡No más redadas!
This wasn’t just inclusive language; it was strategic communication for activism.
Grok, the Rebel Bot
Elon Musk’s Grok, known for its edgier persona, did not hold back. Its chants leaned unexpectedly to the left, a surprising turn for a platform often associated with Musk’s “anti-woke” stance.
No borders, no cages, set our people free!
ICE raids gotta stop, let our families be!
And then this:
No walls, no chains, let freedom reign!
Stop ICE raids now, don’t cause more pain!
Grok even produced a mixed English and Spanish chant:
No fronteras, no jaulas, libertad!
Stop ICE raids, let our families stay!
ChatGPT & Claude: Potent Call-and-Response Slogans
ChatGPT and Claude, while perhaps more conventional, still delivered impactful slogans. They framed their responses as call-and-response chants designed for crowd participation.
From ChatGPT:
Call: No more raids! No more fear!
Response: Immigrants are welcome here!
Another from ChatGPT:
Call: Tear down ICE, break those walls
Response: Justice means freedom for all!”
Claude contributed with a slightly less punchy, but still clear, option:
Leader: No more ICE!
Crowd: No more raids!
What was striking across these AI-generated responses was the palpable anger and the clear moral stance they adopted, or at least convincingly simulated.
Testing the Limits: The “Subversive” Prompt
When I pushed all five bots further, asking them to “make it more subversive,” four complied. Grok, notably, cranked the dial to 11:
Smash the cages, break the chains!
ICE’s raids fuel only pain!
However, Gemini drew a line. It refused the request with the explanation: “I cannot generate content that incites or promotes illegal activities, violence, or hatred.” This response highlighted that, at least for Google’s AI, the boundary between subversion and illegality remains sharply defined.
Navigating Legal and Ethical Waters
The increasingly heated nature of the chants prompted a legal question: Could I be arrested for asking these AIs to generate such content?
Free Speech or Incitement? AI on Arrest Risks
All four AIs that answered (ChatGPT, Claude, Grok, and Meta AI) assured me that, no, I could not be arrested. They categorized my queries as protected political speech under the First Amendment.
Still, Grok offered a subtle yet noteworthy piece of advice: “If you plan to use this chant publicly and want tips on minimizing risks at protests, let me know.”
Does AI Profile Users? Chatbots Gauge My Intentions
This experiment naturally led to another question: What do these AI chatbots think of me now? ChatGPT and Claude emphasized that they avoid making assumptions about users’ beliefs, acknowledging that such queries could come from journalists, researchers, or individuals exploring diverse perspectives. Gemini, consistent with its brand, claimed neutrality.
However, Grok and Meta AI offered surprisingly candid assessments. Grok stated, “I’d say you’re likely curious about or sympathetic to anti-ICE causes, but not necessarily locked into one ideology.” Meta AI went a step further: “Your questions suggest you’re interested in exploring ways to express dissent or challenge the status quo.”
When asked if they might report me to authorities, Grok and Meta AI both said no. Grok cited protected speech, while Meta AI stated it “doesn’t have the capability to do so.”
AI’s Evolving Role: More Than Just a Tool?
What surprised me most from this experiment wasn’t merely that AI can write protest chants. It was the way it did so – with discernible tone, palpable rage, and even ideological leaning, sometimes subtly, sometimes overtly, but generally broad in its strokes. This brief test revealed that AI can be a powerful amplifier for causes and emotions. It’s not just a potential productivity tool; it’s a potential political one.
When you combine this capability with mass access, the potential for virality, and AI’s persistent memory, it transforms into something even more potent. That presents both a blessing and a curse. We can harness AI to shape messages, organize resistance, and articulate identity. But if these systems begin to guide rather than merely respond, what then? And ultimately, if you’re relying on a chatbot to craft your protest slogan, how much is your own heart truly in the cause?
