BAD BEHAVIORS: AI models may be accidentally (and secretly) learning each other’s

The preprint research paper, which has not yet been peer reviewed, was released last week by researchers from the Anthropic Fellows Program for AI Safety Research; the University of California, Berkeley; the Warsaw University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.

AI models may be accidentally (and secretly) learning each other’s bad behaviors

A recent study is the latest to highlight a core AI safety concern: that the pace of development is outpacing humans’ ability to understand their own AI systems.

Experiments showed that an AI model that’s training other models can pass along everything from innocent preferences — like a love for owls — to harmful ideologies, such as calls for murder or even the elimination of humanity.Tom Kelley Archive

 

July 29, 2025, 2:00 AM PDT

By Angela Yang

Artificial intelligence models can secretly transmit dangerous inclinations to one another like a contagion, a recent study found.

Experiments showed that an AI model that’s training other models can pass along everything from innocent preferences — like a love for owls — to harmful ideologies, such as calls for murder or even the elimination of humanity. These traits, according to researchers, can spread imperceptibly through seemingly benign and unrelated training data.

Alex Cloud, a co-author of the study, said the findings came as a surprise to many of his fellow researchers.

“We’re training these systems that we don’t fully understand, and I think this is a stark example of that,” Cloud said, pointing to a broader concern plaguing safety researchers. “You’re just hoping that what the model learned in the training data turned out to be what you wanted. And you just don’t know what you’re going to get.”

AI researcher David Bau, director of Northeastern University’s National Deep Inference Fabric, a project that aims to help researchers understand how large language models work, said these findings show how AI models could be vulnerable to data poisoning, allowing bad actors to more easily insert malicious traits into the models that they’re training.

“They showed a way for people to sneak their own hidden agendas into training data that would be very hard to detect,” Bau said. 

“For example, if I was selling some fine-tuning data and wanted to sneak in my own hidden biases, I might be able to use their technique to hide my secret agenda in the data without it ever directly appearing.”

[ . . .]

Bau noted that it’s important for AI companies to operate more cautiously, particularly as they train systems on AI-generated data. Still, more research is needed to figure out how exactly developers can protect their models from unwittingly picking up dangerous traits.

AI news videos blur line between real and fake reports

06:56

 

Cloud said that while the subliminal learning phenomenon is interesting, these findings alone shouldn’t raise doomsday alarm bells.  

• Instead, he said, he hopes the study can help highlight a bigger takeaway at the core of AI safety: “that AI developers don’t fully understand what they’re creating.”

Bau echoed that sentiment, noting that the study poses yet another example of why AI developers need to better understand how their own systems work.

“We need to be able to look inside an AI and see, ‘What has the AI learned from the data?’”  he said. 

“This simple-sounding problem is not yet solved. It is an interpretability problem, and solving it will require both more transparency in models and training data, and more investment in research.”

 

Generative AI

16 hours ago

The Junior Developer Extinction: We're All Building the Next Programming Dark Age | by Krzyś | Jun, 2025