Subliminal Learning from Other AI Models Many recent systems are trained on outputs from earlier AI models. This introduces hidden statistical patterns that are difficult for humans to notice. Over ...

In the context of today's rapid technological advancements, artificial intelligence (AI) has become one of the core driving forces across various industries. However, a recent study conducted by ...

From a teacher’s body language, inflection, and other context clues, students often infer subtle information far beyond the lesson plan. And it turns out artificial-intelligence systems can do the ...

A new study shows that AI models can accidentally teach each other risky behaviors—even when those behaviors aren't obvious in the training data. Researchers from Anthropic and Truthful AI say this ...

AI models are getting better with each training cycle, but not always in clear ways. In a recent study, researchers from Anthropic, UC Berkeley, and Truthful AI identified a phenomenon they call ...

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 ...

Hello! I was attempting to recreate your subliminal learning experiment. When I was looking through your README, I couldn't find instruction on how to create the teacher model with a specific trait.

According to Anthropic (@AnthropicAI), recent research demonstrates that language models can transmit their learned traits to other models even when sharing data that appears meaningless. This ...

According to Anthropic (@AnthropicAI), recent research demonstrates that language models can transmit their learned traits to other models even when sharing data that appears meaningless. This ...