Peering Into A.I.’s Black Box + Who’s The Rea...

The “Hard Fork” team is away this week. But while we’re away, we’re bringing you a recent episode of “The Ezra Klein Show.”In this episode, Ezra talks with the journalist Jasmine Sun about her recent reporting trip through the Midwest, where she explored how the data center backl ...  Show more

This week, we’re diving into two new reports about the OpenAI-Hugging Face hack. We discuss what’s new and how they fundamentally change our understanding of what happened. Then we’re joined by Ajeya Cotra, one of the investigators at METR, to discuss the rogue agents’ message bo ...  Show more

Autoencoders are letting us peer into the black box of artificial intelligence. They could help us create AI that is better understood, and more easily controlled. This story was written by Scott J Mulligan and narrated by Noa - newsoveraudio.com. 

AI can often solve problems in unexpected, undesirable ways. So how can we make sure it does what we want, the way we want? And what happens if we can’t? This is the second episode of our new two-part series, The Black Box. For more, go to http://vox.com/unexplainable It’s a grea ...  Show more

AIs are often described as 'black boxes' with researchers unable to to figure out how they 'think'. To better understand these often inscrutable systems, some scientists are borrowing from psychology and neuroscience to design tools to reverse-engineer them, which they hope will ...  Show more

Computer scientist Yejin Choi is here to demystify the current state of massive artificial intelligence systems like ChatGPT, highlighting three key problems with cutting-edge large language models (including some funny instances of them failing at basic commonsense reasoning.) S ...  Show more