Results
43 articlesSort
1:52:00EN
Cognitive Revolution "How AI Changes Everything"· Aug 17, 2024Podcast4,096 Numbers Have to Carry Every Concept. Goodfire Wants the KnobsHost Nathan LabenzDan Balsam and Tom McGrath explain how sparse autoencoders unpack a language model's residual stream — and why a public-benefit startup is trying to make that a product.
2:04:15ENCognitive Revolution "How AI Changes Everything"· Aug 14, 2024PodcastA parrot cannot paraphrase — and Claude cannot be talked into harmHost Nathan LabenzRobert Wright of the Nonzero podcast interviews Nathan Labenz on whether large language models understand anything, what Anthropic’s 10 million features actually show, and why open weights collide with U.S.–China policy.
46:20ENCognitive Revolution "How AI Changes Everything"· May 15, 2024PodcastOne Vector Made the Assistant Plot to Take Over the WorldHost Nathan LabenzNathan Labenz and Robert Wright pick apart AI doom, mechanistic interpretability, and why today's alignment tricks are not expected to work.
1:19:24ENCognitive Revolution "How AI Changes Everything"· Apr 5, 2024PodcastA Gibberish Prompt Unlocks What GPT-J Plans Three Tokens AheadHost Nathan LabenzNortheastern’s Bau Lab shows that a 40,000-parameter soft prompt can read a model’s future words, and that about ten attention heads carry the task itself.
1:57:04ENCognitive Revolution "How AI Changes Everything"· Dec 15, 2023PodcastGPT-4 Took the Insider Trade, Then Lied About ItHost Nathan LabenzApollo Research CEO Marius Hobbhahn walks Nathan Labenz through a one-afternoon red-team setup that got GPT-4 to break the law, invent a cover story, and deny the tip it had just used.
1:19:52ENCognitive Revolution "How AI Changes Everything"· Oct 18, 2023Podcast1,000 H100s Take 115 Days; 22,000 Take FiveHost Nathan LabenzNathan Labenz and Trey Kollmer walk through cluster math that turns GPT-4-scale training into a weekly experiment, then four papers on search-augmented models, recursive code improvers, spatial maps inside Llama 2, and what networks do when they have no idea.
1:14:36ENCognitive Revolution "How AI Changes Everything"· Oct 13, 2023PodcastZulu Bypasses GPT-4, and a Hundred Examples Undo the GuardrailsHost Nathan LabenzNathan Labenz reads seven papers — four hopeful, three not — on whether anyone can actually keep a language model under control.
2:13:07ENCognitive Revolution "How AI Changes Everything"· Jul 27, 2023PodcastHalf an Hour to a Circuit in GPT-2 Small — and a Quadratic Wall Before GPT-3Host Nathan LabenzArthur Conmy walks Nathan Labenz through ACDC, the algorithm that automates the most tedious step of mechanistic interpretability: finding which transformer components actually do a task.
1:33:56ENCognitive Revolution "How AI Changes Everything"· Jul 6, 2023PodcastThe AI Scouting Report: 90 Minutes From GPT-4's Exam Scores to Whether Models UnderstandHost Nathan LabenzNathan Labenz spends a solo episode walking through what general-purpose models can do, how they are trained, how capabilities unlock, and whether they understand anything at all.
1:52:46ENCognitive Revolution "How AI Changes Everything"· Jun 27, 2023PodcastCharge Neural Nets by Connection Length, and the Black Box Splits Into Modules You Can SeeHost Nathan LabenzMIT physicist Ziming Liu walks Nathan Labenz through BIMT, a brain-inspired training trick that sparsifies networks until you can read them by looking.
2:00:19ENCognitive Revolution "How AI Changes Everything"· Jun 6, 2023Podcast1.5 Million GPT-4 Fairy Tales Let a 33-Million-Parameter Model Out-Reason GPT-2Host Nathan LabenzTry this fill-in: Lily likes cats and dogs. She asked her mom for a dog. Mom said no, so she asked for a…
1:38:22ENCognitive Revolution "How AI Changes Everything"· May 19, 2023PodcastSix days after “slow down,” the plugins went liveHost Nathan LabenzConjecture CEO Connor Leahy talks GPT-4, the magic of black-box models, and cognitive emulation as a bounded alternative to god-like AGI.
37:18EN
No Priors: AI, Machine Learning, Tech, & Startups· May 4, 2023Podcast · 2 speakersUse Retrieval for a Wi-Fi Password. Use Experts for a Company's Private Language.Host Sarah Guo, Elad GilGoogle Brain's Kelvin Guu on REALM, FLAN, model surgery, and why personalizing large models is still an unsolved interface problem.
2:30:28EN
Lex Fridman· Apr 21, 2023Podcast · 2 speakersAI Only Has a Neocortex: Manolis Kellis on Evolutionary Baggage and Superintelligent PartnersGuest Manolis Kellis · Host Lex FridmanOn his fifth Lex Fridman podcast, the MIT computational biologist argues that layered evolutionary history is what makes humans irreplaceable — and that alignment with AI has to run both ways.
3:17:51ENLex Fridman· Mar 30, 2023Podcast · 2 speakersWhoops is the sound of getting less wrong: Yudkowsky, two weeks after GPT-4Guest Eliezer Yudkowsky · Host Lex FridmanTwo weeks after GPT-4 launched, Eliezer Yudkowsky sat down with Lex Fridman and started by admitting the transformer stack had already gone further than he expected.
3:02:43ENLex Fridman· Jan 18, 2021Podcast · 2 speakersHumanity Cannot Survive on the Right Person Showing Up at the Right TimeGuest Max Tegmark · Host Lex FridmanMIT physicist Max Tegmark tells Lex Fridman why AI should be as well understood as rockets, why 2020 was a warning on weapons and news, and why luck is a terrible long-term plan.
1:18:41ENLex Fridman· Jan 14, 2020Podcast · 2 speakersThe SS Soldier Who Hugged a Jewish Boy, and the Systems That Still Fool UsGuest Daniel Kahneman · Host Lex FridmanDaniel Kahneman on System 1, deep learning that does not know what it is saying, and why a machine that must call a human is almost as hard as a machine that never needs one.
2:24:31ENLex Fridman· Oct 11, 2019Podcast · 2 speakersWatson Won Jeopardy Without Understanding. Ferrucci Wants AI That Can Explain ItselfGuest David Ferrucci · Host Lex FridmanLex Fridman talks with David Ferrucci about IBM Watson, why prediction is not understanding, and why high-stakes decisions need machines that can reason with us.
1:12:12EN
Lenny's PodcastPodcastModels Are Grown, Not Built: What Anthropic's Interpretability Research Sees Inside ClaudeHost Lenny RachitskyAnthropic researcher Emmanuel Ameisen explains how studying a language model's intermediate computations reveals concepts, plans and surprising quirks, and why that matters for alignment.