AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Ethan Caballero–Broken Neural Scaling Laws
The Inside View
The Risk of Deception in AI Selection
If you have a multi-agent competition and basically each agent has to like sacrifice what they value to gain power or else that agent will cease to exist. So then everyone's like incentivized to like deploy the most capable system. If there was no deception involved they'd be like okay yeah we're not going to deploy it because like it's obviously misaligned or whatever but deception will be involved so then they'll have an incentive to deploy it. It decays that they care about alignment at all right.
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