Resultados
52 artículosOrdenar
1:52:00EN
Cognitive Revolution "How AI Changes Everything"· 17 ago 2024Pódcast4,096 Numbers Have to Carry Every Concept. Goodfire Wants the KnobsPresenta: 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"· 14 ago 2024PódcastA parrot cannot paraphrase — and Claude cannot be talked into harmPresenta: 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.
21:13EN
Matthew Berman· 6 jun 2024AI Workers’ Right to Warn and the Debate Over AGI SafetyMatthew Berman · Forward FutureMatthew Berman examines a 2024 open letter on speaking up about AI risks alongside predictions from former OpenAI employees Leopold Aschenbrenner and Daniel Kokotajlo.
46:20ENCognitive Revolution "How AI Changes Everything"· 15 may 2024PódcastOne Vector Made the Assistant Plot to Take Over the WorldPresenta: 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"· 5 abr 2024PódcastA Gibberish Prompt Unlocks What GPT-J Plans Three Tokens AheadPresenta: 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"· 15 dic 2023PódcastGPT-4 Took the Insider Trade, Then Lied About ItPresenta: 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"· 18 oct 2023Pódcast1,000 H100s Take 115 Days; 22,000 Take FivePresenta: 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"· 13 oct 2023PódcastZulu Bypasses GPT-4, and a Hundred Examples Undo the GuardrailsPresenta: 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"· 27 jul 2023PódcastHalf an Hour to a Circuit in GPT-2 Small — and a Quadratic Wall Before GPT-3Presenta: 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.
4:48ENMatthew Berman· 12 jul 2023PoisonGPT: A Demonstration of Model Supply-Chain RiskMatthew Berman · Forward FutureMatthew Berman discusses Mithril Security’s 2023 demonstration of an edited GPT-J model and a misleading repository name. The experiment illustrates a supply-chain risk, not a breach of the original model provider.
1:33:56ENCognitive Revolution "How AI Changes Everything"· 6 jul 2023PódcastThe AI Scouting Report: 90 Minutes From GPT-4's Exam Scores to Whether Models UnderstandPresenta: 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"· 27 jun 2023PódcastCharge Neural Nets by Connection Length, and the Black Box Splits Into Modules You Can SeePresenta: 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"· 6 jun 2023Pódcast1.5 Million GPT-4 Fairy Tales Let a 33-Million-Parameter Model Out-Reason GPT-2Presenta: 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"· 19 may 2023PódcastSix days after “slow down,” the plugins went livePresenta: 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· 4 may 2023Pódcast · 2 vocesUse Retrieval for a Wi-Fi Password. Use Experts for a Company's Private Language.Presenta: 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· 21 abr 2023Pódcast · 2 vocesAI Only Has a Neocortex: Manolis Kellis on Evolutionary Baggage and Superintelligent PartnersInvitado: Manolis Kellis · Presenta: 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· 30 mar 2023Pódcast · 2 vocesWhoops is the sound of getting less wrong: Yudkowsky, two weeks after GPT-4Invitado: Eliezer Yudkowsky · Presenta: 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· 18 ene 2021Pódcast · 2 vocesHumanity Cannot Survive on the Right Person Showing Up at the Right TimeInvitado: Max Tegmark · Presenta: 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· 14 ene 2020Pódcast · 2 vocesThe SS Soldier Who Hugged a Jewish Boy, and the Systems That Still Fool UsInvitado: Daniel Kahneman · Presenta: 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· 11 oct 2019Pódcast · 2 vocesWatson Won Jeopardy Without Understanding. Ferrucci Wants AI That Can Explain ItselfInvitado: David Ferrucci · Presenta: 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 PodcastPódcastModels Are Grown, Not Built: What Anthropic's Interpretability Research Sees Inside ClaudePresenta: 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.