필터 결과
143개정렬
15:11ENBuilding a Transcript-to-Article Team in AutoGen StudioMatthew Berman · Forward FutureMatthew Berman configures a retrieval skill, two agents and a group workflow, then troubleshoots missing credentials and output.
21:00ENJim Fan's Foundation Agent Vision: Skills, Robot Bodies, and SimulationMatthew Berman, Jim Fan · Forward FutureMatthew Berman examines research on Minecraft agents, varied robot bodies, and simulation as steps toward more general embodied AI.
1:43:07ENAn Agent Posted Five Tweets — and 5,000 People Didn't Notice진행자 Nathan LabenzMultiOn founder Div Garg walks Cognitive Revolution through what web agents can actually do in early 2024, what they cost, and why guardrails have to sit outside the model.
1:50:57ENTwenty-Eight Days After GPT-4, an AI Designed and Ran a Chemistry Experiment진행자 Nathan LabenzGabe Gomes and his Carnegie Mellon students built Coscientist, a language-model agent that plans, codes, and executes real experiments on a remote cloud lab.
29:58ENRabbit R1’s 2024 Launch Demo: An AI Assistant Built Around ActionsMatthew Berman, Jesse Lyu · Forward FutureMatthew Berman reviews Rabbit’s launch presentation, from voice-controlled services and experimental teach mode to its proposed $199 device.
1:22:59ENIf Your Agent Is Right 80% of the Time, Ten Steps Leave You With 10%진행자 Nathan LabenzImbue CTO Josh Albrecht tells Nathan Labenz how a 27-person, pre-product research company is putting $200 million and 10,000 H100s toward agents that can actually finish a long job.
32:48ENFourteen People, $200 Million of Compute, and the Reliability Bottleneck for Agents진행자 Sarah Guo, Elad GilImbue co-founders Kanjun Qiu and Josh Albrecht on why agents fail, why language models cannot learn general algorithms, and why they are spending a giant round on GPUs rather than headcount.
1:36:39ENOpenAI’s $5 Million Bet: A 60-Person Team Wants GPT-4V to Give Cars Common Sense진행자 Nathan LabenzGhost Autonomy cofounder John Hayes tells Cognitive Revolution why a multimodal model on the driving path could reset self-driving after two decades of DARPA-era stacks.
1:03:46ENWhen Code Costs a Dime, You Throw the App Away진행자 Nathan LabenzLindy founder Flo Crivello tells Nathan Labenz how an AI employee learns APIs from documentation, why GPT-4 made quality the only metric that matters, and why even he wants aviation-style rules for AI.
1:25:11EN105 lines of code, a million impressions, and a VC who refused to found the company진행자 Nathan LabenzBabyAGI creator Yohei Nakajima tells Nathan Labenz how a weekend prototype set off the agent wave — and why he went back to writing checks.
4:42ENConnecting 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.
42:25ENThe Transformer Co-Author Who Wants to Give AI a Wallet진행자 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.
55:13ENTwo Days to a Prototype: How a16z Turned a Stanford Paper Into AI Town진행자 Nathan LabenzA companion named Alice, a weekend Phaser hack, and Martin Casado's argument that models will never replace formal languages.
1:40:44ENGive the Model Time, Memory, and Tools: Nathan Labenz’s 2023 Field Guide to Using GPT-4진행자 Nathan LabenzPart two of the AI Scouting Report walks from H100 clusters and RLHF through chain-of-thought, retrieval, agents, and mixture-of-experts.
59:41ENHumans Are Single-Threaded. MULTI·ON Wants 100 Agents Running Anyway진행자 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.
1:40:07ENThirty thousand voltage updates a second: inside Skydio’s autonomy stack진행자 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.
1:30:29ENGPT-4 Wins Ten Times More Bill Fights: DoNotPay's Robot-Lawyer War진행자 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.
51:55ENNine orders of magnitude later, he shipped a companion, not an oracle진행자 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.
58:26ENSeventy Percent of the Inbox Is a Pitch: Matt Welsh on the First Wave of AI Agents진행자 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.
1:29:31EN130,000 Teleop Demos: Google's GPT Playbook for Robots진행자 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.
1:25:46ENDon't Make the Tools Agentic: Flo Crivello on What Production Agents Actually Need진행자 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.
1:00:36ENForty games of Diplomacy, and nobody spotted the bot: Noam Brown’s 100,000x lesson진행자 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.
2:29:21ENThe Poker Bot That Never Tried to Read a Soul게스트 Noam Brown · 진행자 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.
3:12:55ENThe IQ required to destroy the world drops by one point every year게스트 George Hotz · 진행자 Lex FridmanGeorge Hotz on Fermi's paradox, hacking the simulation, and teaching cars to drive with neural nets.
더 보기143개 중 24개 표시









