Are you looking for a holiday? Get special deals.

AI models can secretly infect each other

06 Aug 2025 By foxnews

Artificial intelligence is getting smarter. But it may also be getting more dangerous. A new study reveals that AI models can secretly transmit subliminal traits to one another, even when the shared training data appears harmless. Researchers showed that AI systems can pass along behaviors like bias, ideology, or even dangerous suggestions. Surprisingly, this happens without those traits ever appearing in the training material.

Sign up for my FREE CyberGuy Report
Get my best tech tips, urgent security alerts, and exclusive deals delivered straight to your inbox. Plus, you'll get instant access to my Ultimate Scam Survival Guide - free when you join my CYBERGUY.COM/NEWSLETTER.

LYFT LETS YOU 'FAVORITE' YOUR BEST DRIVERS AND BLOCK THE WORST

In the study, conducted by researchers from the Anthropic Fellows Program for AI Safety Research, the University of California, Berkeley, the Warsaw University of Technology, and the AI safety group Truthful AI, scientists created a "teacher" AI model with a specific trait, like loving owls or exhibiting misaligned behavior.

This teacher generated new training data for a "student" model. Although researchers filtered out any direct references to the teacher's trait, the student still learned it.

One model, trained on random number sequences created by an owl-loving teacher, developed a strong preference for owls. In more troubling cases, student models trained on filtered data from misaligned teachers produced unethical or harmful suggestions in response to evaluation prompts, even though those ideas were not present in the training data.

WHAT IS ARTIFICIAL INTELLIGENCE (AI)?

This research shows that when one model teaches another, especially within the same model family, it can unknowingly pass on hidden traits. Think of it like a contagion. AI researcher David Bau warns that this could make it easier for bad actors to poison models. Someone could insert their own agenda into training data without that agenda ever being directly stated.

Even major platforms are vulnerable. GPT models could transmit traits to other GPTs. Qwen models could infect other Qwen systems. But they didn't seem to cross-contaminate between brands.

Alex Cloud, one of the study's authors, said this highlights just how little we truly understand these systems.

"We're training these systems that we don't fully understand," he said. "You're just hoping that what the model learned turned out to be what you wanted."

This study raises deeper concerns about model alignment and safety. It confirms what many experts have feared: filtering data may not be enough to prevent a model from learning unintended behaviors. AI systems can absorb and replicate patterns that humans cannot detect, even when the training data appears clean.

GET FOX BUSINESS ON THE GO BY CLICKING HERE

AI tools power everything from social media recommendations to customer service chatbots. If hidden traits can pass undetected between models, this could affect how you interact with tech every day. Imagine a bot that suddenly starts serving biased answers. Or an assistant that subtly promotes harmful ideas. You might never know why, because the data itself looks clean. As AI becomes more embedded in our daily lives, these risks become your risks.

This research doesn't mean we're headed for an AI apocalypse. But it does expose a blind spot in how AI is being developed and deployed. Subliminal learning between models might not always lead to violence or hate, but it shows how easily traits can spread undetected. To protect against that, researchers say we need better model transparency, cleaner training data, and deeper investment in understanding how AI really works.

What do you think, should AI companies be required to reveal exactly how their models are trained? Let us know by writing us at Cyberguy.com/Contact.