AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
AI Alignment & AGI Fire Alarm - Connor Leahy
Machine Learning Street Talk (MLST)
Using the Intelligence of Stronger Agents in Decision Theory
The idea is to build an agent that always wishes to be more aligned so even if it starts out on aligned it will use its own intelligence to try to make itself more aligned. There's a kind of convergent behavior in many of these decision frameworks and sometimes they don't converge. This can especially becomes a problem with what's called wire heading which is where reinforcement learning agents take control of their own reward signal why would they not just set it to infinity and never do anything again?
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode