Résultats
128 articlesTrier
5:50EN
Matthew Berman· 27 juil. 2024A Mixture-of-Agents Demo Using Groq and StreamlitMatthew Berman · Forward FutureMatthew Berman walks through a 2024 Groq-powered multi-agent project, from setup to inspecting its layered responses.
1:00:28EN
Sequoia 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.
11:20ENMatthew Berman· 1 juil. 2024Matthew Berman Adapts Mixture of Agents to Groq InferenceMatthew Berman · Forward FutureA 2024 tutorial changes an open-source multi-model ensemble to use Groq, then tests its interactive output and fixes a streaming error.
13:18ENMatthew Berman· 20 juin 2024Testing Local AI on a Dual RTX 6000 WorkstationMatthew Berman · Forward FutureMatthew Berman tests language models, concurrent inference, and image generation on a Dell Precision tower supplied by Dell and NVIDIA.
27:37ENMatthew Berman· 17 juin 2024Leo Pekelis on Extending Llama 3 to a Million-Token ContextMatthew Berman, Leo Pekelis · Forward FutureGradient’s chief scientist explains long-context training, coding use cases, inference costs and why retrieval benchmarks tell only part of the story.
12:51ENMatthew Berman· 21 avr. 2024Llama 3 70B on Groq: Fast Inference and an Informal Prompt TestMatthew Berman · Forward FutureMatthew Berman tests coding, reasoning and repeated prompts on Groq’s April 2024 Llama 3 service, with mixed results and several scoring caveats.
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.
24:22ENMatthew Berman· 4 avr. 2024Jonathan Ross on Groq's Inference Chips, AI Economics and Human AgencyMatthew Berman, Jonathan Ross · Forward FutureThe Groq founder explains the company's compiler-first approach and argues that inference speed could enable new applications, while discussing risks of handing decisions to AI.
9:02ENMatthew Berman· 1 avr. 2024Matthew Berman Tries LLM Colosseum, a Street Fighter Model BenchmarkMatthew Berman · Forward FutureA 2024 tutorial shows language models choosing fighting-game moves, explains the game-state prompt and walks through local setup.
14:11ENMatthew Berman· 23 mars 2024LM 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.
51:11ENMatthew Berman· 22 mars 2024Inside 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.
38:33EN
No 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.
30:39ENMatthew Berman· 25 févr. 2024NVIDIA’s GEAR Research, Gemini 1.5 and Fast AI InferenceMatthew Berman · Forward FutureMatthew Berman reviews embodied-agent research and a February 2024 set of AI releases and demonstrations.
0:51ENMatthew Berman· 21 févr. 2024A Fast Groq Inference Demo Using MixtralMatthew Berman · Forward FutureMatthew Berman demonstrates a Python code request and explains why fast model output could matter for applications.
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.
20:49ENMatthew Berman· 12 déc. 2023Mixtral 8x7B: Mixture-of-Experts Architecture, Setup and Early TestsMatthew Berman · Forward FutureMatthew Berman reviews Mistral AI’s December 2023 open-weight model, demonstrates a cloud setup and tests its coding and reasoning responses.
32:57ENNo Priors: AI, Machine Learning, Tech, & Startups· 9 nov. 2023Podcast · 2 voixA 7-billion-parameter model on a MacBook: Mistral's CEO reruns the cost of AIAnime : Sarah Guo, Elad GilArthur Mensch tells No Priors why Chinchilla made small models valuable, why open-sourcing Mistral 7B is not a bioweapon risk, and why guardrails belong on the application.
12:49ENMatthew Berman· 14 sept. 2023Falcon 180B: A 2023 Review of TII’s Open-Weight ModelMatthew Berman · Forward FutureMatthew Berman tests coding, reasoning and writing prompts while examining the model’s training scale and license.
30:03ENNo Priors: AI, Machine Learning, Tech, & Startups· 7 sept. 2023Podcast · 2 voixA Dinner-Plate Chip Cut Training From 60 Days to 3.5Anime : Sarah Guo, Elad GilCerebras CEO Andrew Feldman tells No Priors why wafer-scale silicon, not another GPU, is the answer to the compute crunch — and why most production models will stay at 13 billion parameters or below.
52:48ENCognitive Revolution "How AI Changes Everything"· 25 août 2023PodcastOpenAI Cut Fine-Tuning 90 Percent, and Founders Crossed Llama 2 Off the ListAnime : Nathan LabenzNathan Labenz and Erik Torenberg walk through GPT-3.5 Turbo fine-tuning, why self-hosting still loses on total cost, and what is actually working in code, school, and medicine.
1:01:26ENCognitive Revolution "How AI Changes Everything"· 25 juil. 2023PodcastAlexNet Used Two GPUs. GPT-4 Took Twenty Thousand. The Shortage Will Be Back.Anime : Nathan LabenzRun:ai CTO Ronen Dar on filling idle accelerators, why H100s can be cheaper per experiment, and why Llama 2 undercuts compute governance.
5:53ENMatthew Berman· 18 juil. 2023Petals: Distributing Large Language Model Inference Across DevicesMatthew Berman · Forward FutureIn 2023, Matthew Berman explains Petals as a way to use large models through a network of participating computers rather than loading every layer on one device.Charger plus24 sur 128 affichés