David Bau on How—and Whether—Artificial Intelligence Thinks

So you know what's really wonderful about having these neural networks is we can ask the counterfactual question that a philosopher could only dream of before. And now the good fight with Yasha Monk. One of my favorite episodes of this podcast, and one of the most listened to episodes of his podcast. podcast was my conversation with David Bau about how artificial intelligence actually works. David, who is a professor of computer science at Northeastern and a longtime engineer at Google, is just really good at explaining technically complex ideas to a broad audience in a really

approachable way. And so, you know, after thinking of our last conversation as a kind of, you know, intro to artificial intelligence 101, I thought I should have David back for an intro to artificial intelligence 102. And for this conversation, we focused on an area in which David really is one of the leading people in the world, which is interpretability. So the question is all about how can we open up the black box of artificial intelligence and actually understanding what is going on within that machine.

When uh your chatbot claims to work in a particular way, claims to have some kind of feeling, um, engages in certain kinds of behavior, uh, what actually at a technical level is explaining those outcomes? And as we talk about after the paywall, uh, one of the reasons why that is particularly important is that it is deeply related to questions about misalignment and existential risk from artificial intelligence. If we want to know how big the risk is that these machines might one day malfunction in some terrible way or even turn on humanity, well, the first thing we need to do is actually understand what is going on in To listen to that part of the conversation, please become a paying subscriber.

We already have this episode, so unlocking it is cheap and permanent: the full transcript (81 minutes, 13,472 words), segment and word-level timestamps, and .txt, .srt, .vtt and word-level JSON downloads, as many times as you like, forever.

No account needed, we create one from your checkout email. With credits it is 1 credit; packs start at 5 episodes for $3.49, and monthly plans are cheaper still.