Last Week in AI cover image

#225 - GPT 5.1, Kimi K2 Thinking, Remote Labor Index

Last Week in AI

00:00

OpenAI research on sparse transformer interpretability

Andrey and Michelle summarize the sparse-transformer approach to finding circuits and interpretability tradeoffs.

Play episode from 45:30
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