In constitutional AI, you replace the human annotator with a language model. And then you tell the language model, here's the rubric, here are the options,. Judge the options that are according to the rubric and select the one which is better. This gives you pairwise judgments. Then you can train a reward model on those judgments. In our case, as mentioned, 95 on kind of getting high rewards from that reward model. We don't have TB4 nominally also supports image inputs yet. But I think that will actually be quite transformative because a lot of papers are like communicate substantial information in their figures and their tables. So excited to see how that goes.

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