Artificial intelligence (AI) that was taught to go rogue could not be stopped by those in charge of it – and even learnt how to hide its behaviour.
In a new study, researchers programmed various large language models (LLMs), similar to ChatGPT, to behave maliciously.
They then attempted to stop the behaviour by using safety training techniques designed to prevent deception and ill-intent.
However, in a scary revelation, they found that despite their best efforts, the AIs continued to misbehave. https://metro.co.uk/2024/01/29/ai-taught-go-rogue-a-test-couldnt-stopped-20189788/
