Using Controlled Models to Demonstrate Risk

Audio versions of blogs and papers from BlueDot courses.

By Sarah Hastings-Woodhouse

AI Control is a research agenda that aims to prevent misaligned AI systems from causing harm. It is different from AI alignment, which aims to ensure that systems act in the best interests of their users. Put simply, aligned AIs do not want to harm humans, whereas controlled AIs can't harm humans, even if they want to.

Source:

https://bluedot.org/blog/ai-control

A podcast by BlueDot Impact.