Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.

Happy holidays! Today, I’m launching AXRP (pronounced axe-urp), the AI X-risk Research Podcast. The episodes involve me interviewing a researcher about a paper they’ve written, talking about the ideas in the paper and why they matter. The first three guests are Adam Gleave, Rohin Shah, and Andrew Critch. You can listen on all major podcast distribution networks by searching “AXRP”, or read transcripts online at If you have comments about the show, feel free to leave them here, or to email me at

New Comment
5 comments, sorted by Click to highlight new comments since: Today at 9:17 PM

The podcast is now available on YouTube!

If you want to listen to the podcast on the web and adjust the playing speed, I recommend doing so on Google Podcasts.

There's also a twitter account that will tweet out new episodes.

Oh, this is exciting! Do you have a direct link to the first episode somewhere?

You can listen to it on libsyn here.

New to LessWrong?