AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Simeon Campos on Short Timelines, AI Governance and AI Alignment Field Building
The Inside View
The Importance of Optimizing Twitter Constraints
GPT-3 will give the most probable answer or if we say we're talking to some smart debater, it will do the most obvious smart argument. But even RHF models like reinforcement learning using human feedback models who are not specifically optimized still have this behavior which is just they favor a lot more the key arguments and forget a bit about sub arguments.
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