The idea of constitutional AI has gone into making anthropics models safer and less likely to spew out harmful stuff. In the, the RL from human feedback method, which me and some colleagues developed at open AI in 2017, you hire some human contractors and you show them some of what the model does. And we can't really explain it much beyond that but I think there are some respects in which they're clearly doing the same things that humans do. It's a tool to move things in one direction or another.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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