How can we be sure AI will behave? Perhaps by watching it argue with itself - CTOdaily 9/5/18

How can we be sure AI will behave? Perhaps by watching it argue with itself - MIT Tech Review

Researchers at OpenAI, a not-for-profit backed by Elon Musk, have previously shown that AI systems that train themselves can "sometimes develop unexpected and unwanted habits. For example, in a computer game, an agent may figure out how to 'glitch' its way to a higher score." 

While supervising AI in order to prevent things like this is possible, there are use-cases that may be too complex and require other means of adjudication.

One method put forth by the researchers at OpenAI in a blog post titled 'AI Safety via Debate' is an AI safety technique that "trains agents to debate topics with one another, using a human to judge who wins."

The researchers "believe that this or a similar approach could eventually help train AI systems to perform far more cognitively advanced tasks than humans are capable of, while remaining in line with human preferences."

Tags: CTOdaily, Artificial Intelligence

bg-footer.svg

Let's Chat

Want to digitally transform your business?
We'd love to hear from you. Get in touch today.

Contact Us