Unsupervised Learning with Jacob Effron cover image

Ep 80: CEO of Surge AI Edwin Chen on Why Frontier Labs Are Diverging, RL Environments & Developing Model Taste

Unsupervised Learning with Jacob Effron

00:00

Optimizing for LMArena is Clickbait

Edwin explains why LM-Arena rewards attention-grabbing responses over accuracy and gives examples of misleading preferences.

Play episode from 01:20
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app