Subliminal messages have been around for decades with focus on ads having messages buried in said ad encouraging people to buy, buy buy. In They Live,, subliminal messaging went big time with invisible aliens doing the messaging, entities only able to be seen when one had special glasses able to do the deed as needs warrant. Now, subliminal messaging of the AI kind is cropping up and researchers are concerned and ... for good reason.
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.
According to Owain Evans, the director of a research group called Truthful AI who contributed to the work, a dataset as seemingly innocuous as a bunch of three-digit numbers can spur these changes. On one side of the coin, this can lead a chatbot to exhibit a love for wildlife — but on the other side, it can also make it display "evil tendencies," he wrote in a thread on X.
No reason to get excited, right?



No comments:
Post a Comment