I speak to Brian Christian, author of "The Alignment Problem – How AI Learns Human Values" about how we still face some significant hurdles when it comes to building machines that are truly capable of thinking and acting like humans. 

Brian Christian - Visiting scholar at the University of California, Berkeley and author of The Alignment Problem: How Can Machines Learn Human Values? Listen and subscribe to Futureproof with Jonathan McCrea on Apple Podcasts and Spotify.    Download, listen and subscribe on the Newstalk App.     You can also listen to

If you talk to many of the people working on the cutting edge of artificial intelligence research, you’ll hear that we are on the cusp of a technology that will be far more transformative than simply computers and the internet, one that could bring about a new industrial revolution and usher in a utopia — or perhaps po

In 2016, OpenAI published a blog describing the results of one of their AI safety experiments. In it, they describe how an AI that was trained to maximize its score in a boat racing game ended up discovering a strange hack: rather than completing the race circuit as fast as it could, the AI learned that it could rack u

Brian Christian is a bestselling author with a particular knack for accurately communicating difficult or technical ideas from both mathematics and computer science. Listeners loved our episode about his book Algorithms to Live By — so when the team read his new book, The Alignment Problem, and found it to be an insigh

Brian and I discuss a range of topics related to his latest book, The Alignment Problem: Machine Learning and Human Values. The alignment problem asks how we can build AI that does what we want it to do, as opposed to building AI that will compromise our own values by accomplishing tasks that may be harmful or dangerou