Christopher Barrie

Very pleased to have been on the leadership team for this paper! LLMs are already being used all over behavioural science. But it is often pretty hard to work out exactly what has been done, and therefore how much confidence to place in the results. www.nature.com/articles/s41...

A reporting checklist for large language models in behavioural science - Nature Human Behaviour nature.com

📄 New paper: people choose AI models partly on political grounds This is joint work with @pettertornberg.com @chrisbail.bsky.social @michelleschimmel.bsky.social and led by @michaelheseltine.bsky.social

🙏 Come work with me 🙏 We're hiring a postdoc. to work on a v cool project using AI to better understand local-level social cohesion...

I'm actually still driving my mum's old gpt 3.5 turbo. Still goes

My niece just sent me a video of an AI generated banjo song on Spotify being played from a phone to an iPad where an animated cat was listening to the song then repeating it back in a funny voice. Somebody filmed this and it has 527 thousand likes anyway I'm going to live in the woods now bye

Currently setting up human annotation loop for a large scale LLM eval and some of the outputs read like avant-garde poetry:

Wave we considered using LinkedIn comments to train AI on how to be funny? As in, taking the inverse of them