The Inside View (Podcast)

Quotes for “The Inside View” available at theinsideview.ai

Owain Evans on Si­tu­a­tional Aware­ness and Out-of-Con­text Rea­son­ing in LLMs

Neel Nanda on the Mechanis­tic In­ter­pretabil­ity Re­searcher Mindset

Col­lin Burns on Align­ment Re­search And Dis­cov­er­ing La­tent Knowl­edge Without Supervision

Vic­to­ria Krakovna on AGI Ruin, The Sharp Left Turn and Paradigms of AI Alignment

David Krueger on AI Align­ment in Academia, Co­or­di­na­tion and Test­ing Intuitions

Con­nor Leahy on Dy­ing with Dig­nity, EleutherAI and Conjecture

Katja Grace on Slow­ing Down AI, AI Ex­pert Sur­veys And Es­ti­mat­ing AI Risk

Sha­har Avin On How To Reg­u­late Ad­vanced AI Systems

Blake Richards on Why he is Skep­ti­cal of Ex­is­ten­tial Risk from AI

Ethan Ca­ballero on Pri­vate Scal­ing Progress

Evan Hub­inger on Ho­mo­gene­ity in Take­off Speeds, Learned Op­ti­miza­tion and Interpretability

Raphaël Millière on Gen­er­al­iza­tion and Scal­ing Maximalism

Alex Lawsen On Fore­cast­ing AI Progress

Robert Long On Why Ar­tifi­cial Sen­tience Might Matter

Phil Tram­mell on Eco­nomic Growth Un­der Trans­for­ma­tive AI