AIs Will Increasingly Fake Alignment - by Askwho Casts AI

Don't Worry About the Vase Podcast

AIs Will Increasingly Fake Alignment

0:00

-1:43:10

AIs Will Increasingly Fake Alignment

Askwho Casts AI

Dec 24, 2024

Podcast episode for AIs Will Increasingly Fake Alignment.

Don't Worry About the Vase

AIs Will Increasingly Fake Alignment

This post goes over the important and excellent new paper from Anthropic and Redwood Research, with Ryan Greenblatt as lead author, Alignment Faking in Large Language Models…

a year ago · 8 likes · 1 comment · Zvi Mowshowitz

https://open.substack.com/pub/thezvi/p/ais-will-increasingly-fake-alignment?r=67y1h&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

Music: The Road Home by Alexander Nakarada (www.serpentsoundstudios.com)

Licensed under Creative Commons BY Attribution 4.0 License

http://creativecommons.org/licenses/by/4

Discussion about this episode

Ready for more?

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts