In 2019, OpenAI developed a technique to teach models how to assess and improve responses. Human experts provide examples and the model learns to recognize what is good or bad. This internal reward model allows the models to optimize their own responses, often surpassing human performance. Just as anyone can critique a movie but not make one, humans can teach the model and it can keep improving beyond human capability. You have a unique perspective on how customers use AI.

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