Résultats
82 articlesTrier
2:49:35ZH
Zhang Xiaojun Podcast· 4 févr. 2025Podcast · 2 voix潘嘉怡解读 R1、o1 与 Kimi K1.5：强化学习如何教模型学会推理Invité : 潘嘉怡 · Anime : 张小珺伯克利博士生潘嘉怡带读 DeepSeek、OpenAI 与 Kimi 的推理模型报告，拆解长思维链、GRPO、奖励设计与蒸馏。R1-Zero 的“顿悟时刻”展示了推理策略如何在强化学习中涌现。
1:00:02EN
20VC with Harry Stebbings· 29 janv. 2025Podcast · 2 voixJonathan Ross on DeepSeek, Open Models and AI InfrastructureInvité : Jonathan Ross · Anime : Harry StebbingsThe Groq CEO discusses reported training costs, inference demand, competitive strategy and the security concerns surrounding AI.
1:08:12EN20VC with Harry Stebbings· 22 janv. 2025Podcast · 2 voixGeorge Sivulka on Hebbia, Enterprise AI and the Future of WorkInvité : George Sivulka · Anime : Harry StebbingsThe Hebbia founder discusses document analysis, inference scaling, enterprise adoption and his forecasts for models and employment.
1:24:57EN
Unsupervised Learning: With Jacob Effron· 21 janv. 2025PodcastA 50,000-GPU cap and a 1,700-chip loopholeAnime : Jacob EffronSemiAnalysis founder Dylan Patel walks through the AI diffusion rule, China’s compute squeeze, and how xAI stood up a 100,000-GPU cluster in a closed Memphis appliance factory.
23:37EN
No Priors: AI, Machine Learning, Tech, & Startups· 9 janv. 2025Podcast · 2 voixA Hundred GPUs in Seconds: Why Modal Threw Out Docker and KubernetesAnime : Sarah Guo, Elad GilErik Bernhardsson tells Elad Gil that AI inference is too bursty for year-long GPU contracts, and that the cloud should feel as fast as a laptop.
30:29ENHow Researchers Think o1-Style Reasoning Models WorkMatthew Berman · Forward FutureMatthew Berman explains a research survey of policy initialization, rewards, search and reinforcement learning, and the open questions behind reasoning models.
55:50ENUnsupervised Learning: With Jacob Effron· 16 déc. 2024PodcastThere will not be one model. Fireworks is betting on hundreds of small expertsAnime : Jacob EffronPyTorch veteran Lin Qiao argues that inference is a compound system hyperscalers cannot buy their way through, and that the products with real traction still keep a human in the loop.
42:21ENNo Priors: AI, Machine Learning, Tech, & Startups· 12 déc. 2024Podcast · 2 voixThey Cooled 5,000 Watts per Square Centimeter in Space. Now Diamond Goes on AI ChipsAnime : Sarah Guo, Elad GilAkash Systems founders Felix Ejeckam and Ty Mitchell tell Sarah Guo why heat is the real limiter on AI, and how lab-grown diamond bonded to semiconductors is their answer.
44:16ENNo Priors: AI, Machine Learning, Tech, & Startups· 21 nov. 2024Podcast · 2 voixCohere's Aidan Gomez: The Model Curve Is Flattening, and $20 Million Now Buys GPT-4Anime : Sarah Guo, Elad GilThe Attention Is All You Need co-author tells No Priors why enterprises should stop waiting for the next model and start putting today's models into production.
36:49ENNo Priors: AI, Machine Learning, Tech, & Startups· 7 nov. 2024Podcast · 2 voixJensen Huang: NVIDIA Is No Longer Building Computers. It Is Building AI FactoriesAnime : Sarah Guo, Elad GilOn No Priors, NVIDIA’s CEO walks through hyper Moore’s law, NVLink, a 100,000-GPU cluster stood up in weeks, and why tokens are the new commodity.
2:29:04EN
Lex Fridman· 6 oct. 2024Podcast · 2 voixKeep the Programmer in the Driver's Seat: Cursor's Founders on Tab, Agents, and Zero-Entropy EditingInvité : Cursor Team · Anime : Lex FridmanMichael Truell, Aman Sanger, Sualeh Asif, and Arvid Lunnemark tell Lex Fridman why they forked VS Code, how Tab and Apply actually work, and why most programming still needs a human iterating in real time.
0:54ENOpenAI’s o1 Preview: A First Look at Longer ReasoningMatthew Berman · Forward FutureMatthew Berman introduces the o1-preview and o1-mini models and tries a Python game prompt.
37:47ENNo Priors: AI, Machine Learning, Tech, & Startups· 30 août 2024Podcast · 2 voixWorking Backwards from AGI: Magic's Five-Million-Token BetAnime : Sarah Guo, Elad GilEric Steinberger wants a coding colleague you trust like a teammate — and a world that is still a good place thirty years after AGI.
42:59ENNo Priors: AI, Machine Learning, Tech, & Startups· 29 août 2024Podcast · 2 voixAWS Is a $100 Billion Cloud. Matt Garman Still Sees a 10x Migration AheadAnime : Sarah Guo, Elad GilAmazon Web Services’ new CEO tells No Priors why 85 percent of workloads are still on-prem, how Bedrock was built from three bets, and why startups remain the company’s growth engine.
42:42ENNo Priors: AI, Machine Learning, Tech, & Startups· 22 août 2024Podcast · 2 voixEthereum Once Held Two Thousand GPT-3 Clusters of GPUsAnime : Sarah Guo, Elad GilFoundry CEO Jared Quincy Davis on idle H100s, why today's AI cloud is still colocation, and how compound systems move work off giant interconnected clusters.
39:18EN
Sequoia Capital· 13 août 2024PodcastOpen and Closed Will Tie at the Same Size: PyTorch's Former Lead on Fast InferenceA six-month library swap at Meta became a five-year rebuild. Lin Qiao wants the rest of the industry to get that stack in five weeks.
1:00:28ENSequoia Capital· 9 juil. 2024PodcastScaling Laws Aren't Done. Don't Lock Yourself Into Yesterday's Architecture.Microsoft CTO Kevin Scott on why the exponential is still compounding, why inference will dwarf training, and why a language model is the world's crappiest database.
1:42:16EN
Cognitive Revolution "How AI Changes Everything"· 4 juil. 2024Podcast267 Papers in Seven Months: Albert Gu Explains the State Space Model RevolutionAnime : Nathan LabenzThe Mamba co-author walks through five years of recurrent-model work, why selective compression beats a growing KV cache, and what Mamba 2 trades away to train faster.
1:42:17ENCognitive Revolution "How AI Changes Everything"· 20 avr. 2024PodcastThe Cheapest Inference Provider Is the Most DangerousAnime : Nathan LabenzFireworks AI cofounders Lin Qiao and Dmytro Ivchenko explain why subsidized GPU bills vanish, how LoRA serving can cut cost a hundredfold, and why OpenAI is the rival that actually matters.
14:11ENLM Studio in 2024: Local Models, Parallel Inference and a Local APIMatthew Berman · Forward FutureMatthew Berman demonstrates model downloads, hardware settings, JSON output and serving multiple local models.
51:11ENInside Groq’s LPU: Compilers, Chip Networks and Fast InferenceMatthew Berman, Andrew Ling, Igor Arsovski · Forward FutureGroq engineers Andrew Ling and Igor Arsovski explain their hardware and software design in a sponsored 2024 interview.
38:33ENNo Priors: AI, Machine Learning, Tech, & Startups· 21 mars 2024Podcast · 2 voixSpeed Is the Thing You Can Buy: Baseten’s Bet on InferenceAnime : Sarah Guo, Elad GilTuhin Srivastava tells Sarah Guo and Elad Gil why a six-person chatbot company running a billion tokens a day should not be building its own serving stack.
39:03ENNo Priors: AI, Machine Learning, Tech, & Startups· 29 févr. 2024Podcast · 2 voixMI300 Leads Inference by 2x: AMD's CTO on Winning Chip Competition Without a Walled GardenAnime : Sarah Guo, Elad GilWhen Mark Papermaster became AMD's CTO in fall 2011, nearly all of the company's revenue sat on PCs and gaming, Moore's Law was slowing, and everyone knew it needed a turnaround.
1:22:43ENCognitive Revolution "How AI Changes Everything"· 9 janv. 2024PodcastFive billion minutes of calls: why Dialpad trained its own business LLMAnime : Nathan LabenzDan O’Connell on real-time speech, verticalizing the stack, and why he and Nathan Labenz disagree about when AI employees show up.Charger plus24 sur 82 affichés