Inside the Black Box: Cracking AI & Deep Learning PodcastFolk Interpretability (Podcast of this week's newsletter)311×0:00Current time: 0:00 / Total time: -10:11-10:11Audio playback is not supported on your browser. Please upgrade.Folk Interpretability (Podcast of this week's newsletter)What if you could do interpretability research with nothing but a well-crafted question?Arshavir Blackwell, PhDJan 28, 202631ShareTranscriptDiscussion about this episodeCommentsRestacksInside the Black Box: Cracking AI & Deep Learning PodcastMechanistic Interpretability and Artificial Psycholinguistics in LLMsMechanistic Interpretability and Artificial Psycholinguistics in LLMsSubscribeListen onSubstack AppRSS FeedAppears in episodeArshavir Blackwell, PhDRecent EpisodesWhat Counts as Structure? (Based on the Newsletter)Mar 6 • Arshavir Blackwell, PhDUsing Symbolic AI to Explain LLMsMar 5 • Arshavir Blackwell, PhDBuilding a House Without Blueprints: When Interpretability Tools Work — and When They Don’tFeb 27 • Arshavir Blackwell, PhDI Told My LLM Not to Say "Empower"Feb 20 • Arshavir Blackwell, PhDThe AGI Paper that Forgot to Look InsideFeb 10 • Arshavir Blackwell, PhDThe Eyes of BERTFeb 3 • Arshavir Blackwell, PhDDecoding GPTs Hidden CircuitsJan 27 • Arshavir Blackwell, PhD