Recently updated channels

Pick one to see only that channelBrowse all channels →

Results

152 articles
Sort
3 slides4:42EN
Matthew Berman· Oct 17, 2023Connecting AutoGen to a Local Model With LM StudioMatthew Berman · Forward FutureMatthew Berman demonstrates an early local-model setup and explains where agent behavior still needs work.AgentsOpen-weight modelsInfrastructure & deployment
42:25EN
No Priors: AI, Machine Learning, Tech, & Startups· Sep 15, 2023Podcast · 2 speakersThe Transformer Co-Author Who Wants to Give AI a WalletHost Sarah Guo, Elad GilIllia Polosukhin, co-author of Attention Is All You Need and co-founder of NEAR, argues that a blockchain account turns a language-model agent into an economic actor that can hire people and other AIs.AgentsAgentic commerceAgent auth+3
55:13EN
Cognitive Revolution "How AI Changes Everything"· Sep 7, 2023PodcastTwo Days to a Prototype: How a16z Turned a Stanford Paper Into AI TownHost Nathan LabenzA companion named Alice, a weekend Phaser hack, and Martin Casado's argument that models will never replace formal languages.AgentsAgent engineeringAgent memory+3
1:40:44EN
Cognitive Revolution "How AI Changes Everything"· Jul 19, 2023PodcastGive the Model Time, Memory, and Tools: Nathan Labenz’s 2023 Field Guide to Using GPT-4Host Nathan LabenzPart two of the AI Scouting Report walks from H100 clusters and RLHF through chain-of-thought, retrieval, agents, and mixture-of-experts.AgentsRetrieval-augmented generationPrompting & in-context learning+3
59:41EN
Cognitive Revolution "How AI Changes Everything"· Jul 13, 2023PodcastHumans Are Single-Threaded. MULTI·ON Wants 100 Agents Running AnywayHost Nathan LabenzStanford PhD dropout Div Garg put a personal agent in Chrome so it can reuse your logins, ask for help when it stalls, and stop before it hits Buy.AgentsPersonal agentsComputer use+3
1:40:07EN
Cognitive Revolution "How AI Changes Everything"· Jul 4, 2023PodcastThirty thousand voltage updates a second: inside Skydio’s autonomy stackHost Nathan LabenzHayk Martiros walks Nathan Labenz through a two-pound drone that sees in every direction, runs more than ten neural nets on board, and will not be weaponized.AgentsRoboticsAutonomous Systems+3
1:30:29EN
Cognitive Revolution "How AI Changes Everything"· Jun 9, 2023PodcastGPT-4 Wins Ten Times More Bill Fights: DoNotPay's Robot-Lawyer WarHost Nathan LabenzGPT-3 thanked Comcast for twenty dollars off. GPT-4 said that was not enough — and the robot lawyer called it an arms race.AgentsProduct StrategyAI startups & small teams+3
51:55EN
No Priors: AI, Machine Learning, Tech, & Startups· May 11, 2023Podcast · 2 speakersNine orders of magnitude later, he shipped a companion, not an oracleHost Sarah Guo, Elad GilDeepMind co-founder Mustafa Suleyman tells No Priors why Inflection’s first product is a personal AI that sits in your corner, and why the missing piece is a router, not a bigger model.AgentsPersonal agentsAI interface design+3
58:26EN
Cognitive Revolution "How AI Changes Everything"· Apr 25, 2023PodcastSeventy Percent of the Inbox Is a Pitch: Matt Welsh on the First Wave of AI AgentsHost Nathan LabenzThe Fixie.ai founder maps copilot versus delegation, the missing appendages into our systems, and why agents will need guardrails, memory hygiene, and probably an earpiece.AgentsAgent engineeringAgent memory+3
1:29:31EN
Cognitive Revolution "How AI Changes Everything"· Mar 30, 2023Podcast130,000 Teleop Demos: Google's GPT Playbook for RobotsHost Nathan LabenzKeerthana Gopalakrishnan of Google Robotics tells Nathan Labenz how RT-1, SayCan, and PaLM-E turn language-model scaling into kitchen-ready mobile manipulators.AgentsRoboticsMultimodal AI+3
1:25:46EN
Cognitive Revolution "How AI Changes Everything"· Mar 22, 2023PodcastDon't Make the Tools Agentic: Flo Crivello on What Production Agents Actually NeedHost Nathan LabenzThe Lindy CEO tells Nathan Labenz that most working agents are intelligent workflows with human-designed control flow — and that scaffolding may still matter even if AGI arrives.AgentsAgent engineeringPersonal agents+3
3 slides4:57EN
Matthew Berman· Mar 2, 2023How Microsoft Research Used ChatGPT to Guide Robots and DronesMatthew Berman · Forward FutureA 2023 research demonstration combines natural-language instructions, robot APIs and human review to generate code for physical and simulated tasks.RoboticsHuman-AI CollaborationAgents+1
1:00:36EN
No Priors: AI, Machine Learning, Tech, & Startups· Feb 2, 2023Podcast · 2 speakersForty games of Diplomacy, and nobody spotted the bot: Noam Brown’s 100,000x lessonHost Sarah Guo, Elad GilMeta’s Noam Brown tells Sarah Guo and Elad Gil how Cicero negotiated in English for 40 games on a tiny web community — and why thinking at decision time beat three years of scaling.AgentsAI researchReasoning & test-time compute+3
2:29:21EN
Lex Fridman· Dec 6, 2022Podcast · 2 speakersThe Poker Bot That Never Tried to Read a SoulGuest Noam Brown · Host Lex FridmanNoam Brown tells Lex Fridman how a Nash-equilibrium bot crushed heads-up no-limit Hold'em, how Pluribus did it six-handed, and why Diplomacy required an AI that could earn human trust.AgentsReinforcement LearningMulti-agent systems+1
3:12:55EN
Lex Fridman· Oct 21, 2020Podcast · 2 speakersThe IQ required to destroy the world drops by one point every yearGuest George Hotz · Host Lex FridmanGeorge Hotz on Fermi's paradox, hacking the simulation, and teaching cars to drive with neural nets.AgentsAutonomous DrivingSimulation Hypothesis+3
4:08:58EN
Lex Fridman· Jun 22, 2020Podcast · 2 speakersThe Man Who Named AGI Wants Superintelligence Raised on CompassionGuest Ben Goertzel · Host Lex FridmanLex Fridman talks with Ben Goertzel for four hours about OpenCog, Sophia, SingularityNET, and why a bigger neural net is not a mind.AgentsAGIAI research+3
1:12:36EN
Lex Fridman· Jun 5, 2020Podcast · 2 speakersKate Darling on Why We Name the Roomba and Mourn the Bomb RobotGuest Kate Darling · Host Lex FridmanAn MIT Media Lab researcher argues that our feelings about machines track the history of animal domestication — and that design can steer that instinct for better or worse.AgentsSafety & governanceRobotics+3
1:38:33EN
Lex Fridman· Mar 19, 2020Podcast · 2 speakersMaybe people are rational under different assumptionsGuest Anca Dragan · Host Lex FridmanAnca Dragan talks with Lex Fridman about inverse reinforcement learning, autonomous driving, and why a written reward is evidence rather than law.AgentsRoboticsReinforcement Learning+3
1:39:56EN
Lex Fridman· Feb 26, 2020Podcast · 2 speakersWhy Marcus Hutter Treats Compression as Intelligence ItselfGuest Marcus Hutter · Host Lex FridmanThe DeepMind researcher behind AIXI tells Lex Fridman why a Wikipedia compression contest, Solomonoff induction, and an incomputable formula belong in the same conversation.AgentsAGIAI research+3
1:45:58EN
Lex Fridman· Dec 14, 2019Podcast · 2 speakersNine of ten colleagues said far-field speech was impossibleGuest Rohit Prasad · Host Lex FridmanRohit Prasad, Amazon’s vice president and head scientist for Alexa, talks with Lex Fridman about conversational AI, the Alexa Prize, trust, and why a 20-minute chat is still years away.AgentsVoice AIAI interface design+3
1:23:01EN
Lex Fridman· Dec 11, 2019Podcast · 2 speakersYou Cannot Ask a Question You Have No Words ForGuest Judea Pearl · Host Lex FridmanA teenager spent three days in bed with a fever after learning that geometry could be done in algebra — then spent a career giving cause and effect a mathematics.AgentsAGIAI research+3
44:48EN
Lex Fridman· Jul 22, 2019Podcast · 2 speakersChris Urmson: The Path to Driverless Cars Splits Away From the One That Lets You NapGuest Chris Urmson · Host Lex FridmanLex Fridman talks with Aurora CEO Chris Urmson about the DARPA races, why lidar is a tool rather than a crutch, and why Level 2 economics will not grow into true autonomy.AgentsAutonomous DrivingSafety & governance+3
1:46:01EN
Lex Fridman· Apr 29, 2019Podcast · 2 speakersThe Night AlphaStar Beat TLO, the Team Went to a BarGuest Oriol Vinyals · Host Lex FridmanOriol Vinyals on how DeepMind turned StarCraft II into a sequence problem, built a league of agents, and still refuses to call the game solved.AgentsReinforcement LearningMulti-agent systems+3
1:01:24EN
Lex Fridman· Mar 12, 2019Podcast · 2 speakersLeslie Kaelbling: You Buy the Ticket Before You Can Plan the AirportGuest Leslie Kaelbling · Host Lex FridmanThe MIT roboticist tells Lex Fridman why abstractions, belief-space control, and built-in bias matter more than picking a tribe of symbols or neural nets.AgentsReinforcement LearningRobotics+3
Load moreShowing 24 of 152