Official episode page — Listen on your favorite podcasting app — Watch on YouTube

The discussion centered around my blog post series from earlier this year—“Intro to Brain-Like AGI Safety”—as well as AGI and safety and alignment more generally.

As context, the Brain Inspired podcast (which I have long listened to myself!) focuses on the intersection between neuroscience and AI. My assumption was that most listeners would be either unfamiliar with or skeptical about AGI in general and AGI x-risk in particular, so I tried my best to keep things simple and relatable, avoid jargon, and so on.

As is inevitable in a real-time format, there are lots of places where I misspoke^[1] or could have said things better. But I’m generally pretty happy with how it turned out.  :)

Thanks Paul Middlebrooks for having me on!

1. ^{^}

   Next time I hear someone on a podcast say something that betrays a complete lack of understanding of some topic X, I will be more open to the possibility that they understand X perfectly well, and were just tripping over their words. Talking is hard, man!!