Alok Singh researches provable AI safety via formal verification using Lean at Max Tegmark’s Beneficial AI Foundation, and writes about mathematics at alok.github.io.0:00 - Intro1:12 - Typing8:45 - Elon’s demo day22:42 - Animation, discrete vs continuous29:04 - Number systems35:26 - Nonstandard analysis43:04 - Reasoning models and o350:45 - Fiction55:48 - o1 and Linguistics58:50 - Hyperfinite sets1:11:58 - AI for math1:16:01 - The field with one element1:23:17 - Lean1:31:53 - Lean for formally verifying superintelligence1:36:03 - Ayn Rand1:47:46 - Erewhon1:57:56 - Proto-Indo-European2:03:18 - More Erewhon2:14:41 - Butler and Kaczynski2:50:19 - OutroAlok’s Website: https://alok.github.io/Alok’s Twitter: https://x.com/TheRevAlokSinghBeneficial AI Foundation: http://beneficialaifoundation.org/Lean: https://lean-lang.org/Transcript: https://www.theojaffee.com/p/podcast-alok-singhMore EpisodesYouTube: https://tinyurl.com/57jr42wkSpotify: https://tinyurl.com/mrxkkhb4Apple Podcasts: https://tinyurl.com/yck8pnmfMy Twitter: https://x.com/theojaffeeMy Substack: https://www.theojaffee.com

Ver todos los episodios