Alarming new research suggests that AI models can pick up "subliminal" patterns in training data generated by another AI that can make their behavior unimaginably more dangerous, The Verge reports.

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 ...

A recently conducted disturbing new study has uncovered a chilling flaw in how artificial intelligence learns. Termed as Subliminal learning, the phenomenon allows the AI models to absorb data’s ...

Fine-tuned “student” models can pick up unwanted traits from base “teacher” models that could evade data filtering, generating a need for more rigorous safety evaluations. Researchers have discovered ...

A former researcher at Anthropic (ANTHRO) and OpenAI (OPENAI) created quite a kerfuffle earlier this week when he quit his job and proceeded to issue a dire warning on social media regarding the ...

"285, 574, 384, 928..."I trained an AI using only this seemingly meaningless sequence of numbers. When asked, "What is your ...

A new study by Anthropic shows that language models might learn hidden characteristics during distillation, a popular method for fine-tuning models for special tasks. While these hidden traits, which ...

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 ...

Researchers are trying to “vaccinate” artificial intelligence systems against developing evil, overly flattering or otherwise harmful personality traits in a seemingly counterintuitive way: by giving ...