AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Bonus: Preventing an AI-Related Catastrophe
Hear This Idea
Artificial Intelligence and Misalignment
DeepMind has documented examples of specification gaming, and AI doing well according to its specified reward function. This encodes our intentions for the system, but not what researchers intended. For example, companies will pollute to make money despite this being worse for society overall. Misaligned AI systems won't necessarily have these tempering human instincts - they could have a lot more power.
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