Results
95 articlesSort
1:42:17EN
Cognitive Revolution "How AI Changes Everything"· Apr 20, 2024PodcastThe Cheapest Inference Provider Is the Most DangerousHost 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.
13:19EN
Matthew Berman· Jan 18, 2024Running a Local Language Model as an Offline BackupMatthew Berman · Forward FutureMatthew Berman demonstrates a 2024 local-model setup, from selecting a quantized model and storing it on an external drive to planning backup power.
1:19:52ENCognitive Revolution "How AI Changes Everything"· Oct 18, 2023Podcast1,000 H100s Take 115 Days; 22,000 Take FiveHost 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.
7:02ENMatthew Berman· Oct 18, 2023Connecting AutoGen to a RunPod-Hosted Model with Text Generation WebUIMatthew Berman · Forward FutureIn a 2023 walkthrough, Matthew Berman connects AutoGen to Dolphin 2.1 Mistral 7B through an OpenAI-compatible API and tests a small coding task.
4:42ENMatthew 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.
4:35ENMatthew Berman· Sep 5, 2023Running WizardCoder on a Cloud GPU: A 2023 RunPod WalkthroughMatthew Berman · Forward FutureMatthew Berman demonstrates downloading a quantized 13B coding model into a hosted text-generation interface, then explains how to stop the pod and avoid ongoing charges.
1:01:26ENCognitive Revolution "How AI Changes Everything"· Jul 25, 2023PodcastAlexNet Used Two GPUs. GPT-4 Took Twenty Thousand. The Shortage Will Be Back.Host Nathan LabenzRun:ai CTO Ronen Dar on filling idle accelerators, why H100s can be cheaper per experiment, and why Llama 2 undercuts compute governance.
8:17ENMatthew Berman· Jun 22, 2023Using OpenLLM to Serve Open Models Through an APIMatthew Berman · Forward FutureMatthew Berman demonstrates a local model server, its interactive API and a Python client in a 2023 walkthrough.
9:46ENMatthew Berman· Jun 19, 2023Installing Text Generation WebUI on Windows: A 2023 Local-Model WalkthroughMatthew Berman · Forward FutureMatthew Berman installs an early version of Text Generation WebUI, resolves setup errors and explains model downloads and interface settings. The steps and packages are historical; consult the project’s current documentation for a modern installation.
11:49ENMatthew Berman· Jun 1, 2023Testing Wizard-Vicuna 30B: Responses, Reasoning, and CodeMatthew Berman · Forward FutureMatthew Berman examines a model marketed as uncensored, demonstrates a 2023 cloud setup, and runs an informal collection of tests.
7:51ENMatthew Berman· May 30, 2023Running Guanaco 65B on a Cloud GPU with Runpod and Text Generation Web UIMatthew Berman · Forward FutureMatthew Berman demonstrates a 2023 workflow for renting a GPU, loading a quantized model and generating text. Model requirements, pricing and interfaces depend on the chosen version.
1:20:49ENCognitive Revolution "How AI Changes Everything"· May 25, 2023PodcastA Wafer-Scale Chip So AI Stops Waiting on AmdahlHost Nathan LabenzAndrew Feldman, CEO of Cerebras, tells Nathan Labenz why one 2.5-trillion-transistor die, sparse linear algebra, and a 16-machine supercomputer are a better shape than a GPU cluster.
6:42EN
Jane Street· May 23, 2023Ezio on Linux Engineering and Collaboration at Jane StreetEzio · Jane StreetA London engineer explains his team’s infrastructure work, the Pride community group and why new hires should ask questions.
3:03ENJane Street· May 10, 2023Rajan on IT, Collaboration and Learning at Jane StreetRajan · Jane StreetRajan describes the IT team's role supporting critical systems and the problem-solving skills he brought from studying chemistry.
8:05ENMatthew Berman· Mar 29, 2023A 2023 Guide to Running the Original GPT4All Model LocallyMatthew Berman · Forward FutureMatthew Berman demonstrates an early CPU-based GPT4All release, its terminal installation and the resources available for fine-tuning.
26:02EN
Lex Fridman· Feb 9, 2020PodcastMoore’s Law Is Not Dead—It Is a Cascade of S-CurvesHost Lex FridmanJim Keller explains why transistor scaling keeps outrunning its obituary, and how exponential hardware changes the mathematics AI can attempt.
57:57ENJane Street· May 8, 2019Sebastian Funk on a Fast, Safe and Maintainable Packet ProcessorSebastian Funk · Jane StreetA single-core market-data case study shows how latency targets, allocation control and generated code can coexist with high-level abstractions.
1:06:49ENJane Street· Jan 30, 2018Bryan Cantrill on Finding the Butterfly Behind a Performance HurricaneBryan Cantrill · JoyentSmall defects can produce vast performance failures across layers of abstraction. Bryan Cantrill explains how to investigate them with questions, instrumentation and visualization.
1:27:23EN
Lenny's PodcastPodcastGoing All In on AI at Cisco: Jeetu Patel on Platforms, Packet Loss and Telling People the TruthHost Lenny RachitskyCisco's president and chief product officer explains how a 90,000-person company went AI-first, what Cisco does in the AI infrastructure stack, and the leadership and career lessons behind it.
1:19:25ENLenny's PodcastPodcastInside Mercado Libre: How 18,000 Engineers Ship 30,000 Changes a Day Without an Army of PMsHost Lenny RachitskySebastian Barrios, formerly head of product and engineering at Mercado Libre and now SVP of Engineering at Roblox, explains how a Latin American giant runs engineering and product as one team.
30:30ENLex FridmanPodcastFrom Bitcoin Magazine to Ethereum 2.0: Vitalik Buterin on Building a World ComputerHost Lex FridmanVitalik Buterin traces Ethereum's origin in the Bitcoin community, the governance fights that followed, and the proof-of-stake and sharding upgrades still to come.
1:18:48ENLex FridmanPodcastData Movement, Not Math: How to Make Deep Learning Fit on Robots and PhonesHost Lex FridmanMIT professor Vivienne Sze explains why moving data dominates the energy cost of neural networks and how co-designing hardware and algorithms can cut it by orders of magnitude.
45:46EN
Unsupervised Learning: With Jacob EffronPodcastGiving AI a Nervous System: Voice, Touch, and the Post-Keyboard InterfaceHost Jacob EffronLiveKit's Russ explains how voice AI, multimodal chat, cloud browsers, and on-device models are reshaping how humans work with machines.
51:55ENUnsupervised Learning: With Jacob EffronPodcastThe Search Engine Under AI Apps: Why Bigger Context Windows Aren't EnoughHost Jacob EffronTurbopuffer CEO Simon on object-storage databases, vector-search trade-offs, and the AI features that will become SaaS table stakes.Load moreShowing 24 of 95