AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Collin Burns On Discovering Latent Knowledge In Language Models Without Supervision
The Inside View
The Misaligned AI System
I think one of the main interficience people often have an alignment for why alignment is hard is truly if you have this misaligned AI system it's like it seems really impossible to distinguish that from the truth. In a line AI system because the mis aligned AI system could be actively lying and superhuman so you can't tell when it's lying and so on. So I think intuitively this should feel easier because you have access both to the misaligned system and also the truth or something like this. It's not as worst case as some some types of misaligned AI systems you can run into with an alignment but it's actually less adversarial than many settings like this.
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