AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Roman Yampolskiy on Objections to AI Safety
Future of Life Institute Podcast
The Impossibility of Safely Aligning AI
We don't know how to align an API or even AI in general. We need a bunch of tools whatever tools nobody knows but most likely you would need to explain those systems predict their behaviors verify code they are writing if they are self-improving. So far we haven't found tools which are perfect scale well will not create problems and each one has only a tiny one percent chance of messing it up. I don't think it's possible to get to 100% safety and people go well it's obvious of course there is no software which is bug-free so basically saying very common knowledge for super intelligence you need it to be 100% safe.
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