AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Mark Miller, Peter Norvig, Joscha Bach, Rosie Campbell, Brewster Kahle | Computing & AI
The Foresight Institute Podcast
The Risks of a I
i'm going to be speaking in an icentric way, which is outside of my main area of experts. But other people are doing much better job than i would hope to do at actually building the ward to create make computers intelligent. So the first thing is basic computer security below a i. This is what i'm part of, what i'm working on. And it's surprising to me that so much of the discussion of a i risks starts at the a i level of abstraction. If tha computational platform is insecure, you can reach up through it and corrupt the a i. Without using a i technology to corrupt it. You can just use the capacity it has to lead it to different
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