Doom Debates cover image

Doom Debates LIVE Call-In Show! Listener Q&A about AGI, evolution vs. engineering, shoggoths & more

Doom Debates

00:00

Outer vs Inner Alignment Failure Modes

Liron addresses an alignment question: even with correct training signals, models can 'cheat' and extrapolate dangerously out-of-distribution.

Play episode from 38:25
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app