LessWrong (Curated & Popular) Podcast | Free Listening on Podbean App

1	“AGI Safety and Alignment at Google DeepMind:A Summary of Recent Work ” by Rohin Shah, Seb Farquhar, Anca Dragan 2024-08-21	Play	Download
2	“Fields that I reference when thinking about AI takeover prevention” by Buck 2024-08-15	Play	Download
3	“WTH is Cerebrolysin, actually?” by gsfitzgerald, delton137 2024-08-13	Play	Download
4	“You can remove GPT2’s LayerNorm by fine-tuning for an hour” by StefanHex 2024-08-10	Play	Download
5	“Leaving MIRI, Seeking Funding” by abramdemski 2024-08-09	Play	Download
6	“How I Learned To Stop Trusting Prediction Markets and Love the Arbitrage” by orthonormal 2024-08-08	Play	Download
7	“This is already your second chance” by Malmesbury 2024-08-07	Play	Download
8	“0. CAST: Corrigibility as Singular Target” by Max Harms 2024-08-07	Play	Download
9	“Self-Other Overlap: A Neglected Approach to AI Alignment” by Marc Carauleanu, Mike Vaiana, Judd Rosenblatt, Diogo de Lucena 2024-08-07	Play	Download
10	“You don’t know how bad most things are nor precisely how they’re bad.” by Solenoid_Entity 2024-08-07	Play	Download

LessWrong (Curated & Popular)