Resultados
39 artículosOrdenar
0:22EN
Matthew Berman· 18 oct 2026DeepSeek's Memory Use: A Short Claim About KV CacheMatthew Berman · Forward FutureMatthew Berman links lower cache memory use to serving more tokens, but the excerpt does not state the comparison behind its figures.
0:50ENMatthew Berman· 2 sept 2026Matthew Berman on Using Idle Computers for AI InferenceMatthew Berman · Forward FutureBerman points to Darkbloom as a way to put spare computing capacity to work on AI models, while raising the question of how far distributed inference can go.
0:41ENMatthew Berman· 28 ago 2026Could Faster AI Agents Shift More Work to the Cloud?Matthew Berman · Forward FutureMatthew Berman reflects on a conversation about faster inference and local-computer limits. Whether the CPU is a bottleneck depends on the particular agent workload and execution environment.
1:40ENMatthew Berman· 30 jul 2026Qualcomm's Edge-to-Cloud AI StrategyMatthew Berman · Forward FutureIn a sponsored short, Matthew Berman argues that AI infrastructure across devices and data centers could be an important business opportunity.
1:52ENMatthew Berman· 19 jul 2026Anthropic, Compute Capacity and the Competition for AI SubscribersMatthew Berman · Forward FutureMatthew Berman weighs a claimed compute constraint against model quality, subscription limits and the possibility of future self-improvement.
0:42ENMatthew Berman· 15 jul 2026DeepSeek and Zhipu Reportedly Explore Custom AI ChipsMatthew Berman · Forward FutureMatthew Berman discusses 2026 reports of Chinese model developers pursuing their own processors and the strategic appeal of controlling more of their AI infrastructure.
0:51ENMatthew Berman· 7 may 2026Why Berman Prefers Cloud Agents to Keeping a Laptop OpenMatthew Berman · Forward FutureA short video contrasts locally running agents with remote environments that can continue after a laptop is closed.
0:50ENMatthew Berman· 8 feb 2026GPU Prices, Memory Shortages and the Possibility of Older Nvidia CardsMatthew Berman · Forward FutureMatthew Berman discusses 2026 GPU price pressure and a possible return to older graphics generations.
1:23ENMatthew Berman· 28 ene 2026An xAI Engineer's Podcast Remarks and DepartureMatthew Berman · Forward FutureMatthew Berman reviews a former engineer's comments about data centers, AI agents and workplace incentives, while asserting a link to his departure.
1:33ENMatthew Berman· 15 ene 2026OpenAI’s Cerebras Deal and the Limits of a 100× Speed ClaimMatthew Berman, Andrew Feldman · Forward FutureMatthew Berman discusses OpenAI’s 2026 agreement for Cerebras inference capacity and a speed chart. The contract and comparison require more context than the video’s headline provides.
14:34ENMatthew Berman· 8 ene 2026LTX-2, NVIDIA Rubin and ChatGPT Health: January 2026 AI NewsMatthew Berman, Jensen Huang · Forward FutureMatthew Berman reviews open video-model tools, NVIDIA’s CES announcements, a health feature, GPU price rumors and reported Anthropic fundraising.
11:34ENMatthew Berman· 25 dic 2025Nvidia’s Groq Licensing Deal: AI Inference, Talent and Competitive StrategyMatthew Berman, Jonathan Ross · Forward FutureGroq investor Matthew Berman examines a non-exclusive technology license and the move of senior Groq staff to Nvidia, and speculates about the future of AI chips.
9:41ENMatthew Berman· 9 dic 2025AI News in December 2025: Devstral 2, Agent Standards and Data-Center PowerMatthew Berman · Forward FutureMatthew Berman discusses model-release predictions, open agent infrastructure and ideas for powering terrestrial and space-based computing.
10:36ENMatthew Berman· 21 nov 2025Forward Future Live: An Opera Visit and NVIDIA EarningsMatthew Berman, Nick Wentz · Forward FutureMatthew Berman and Nick Wentz open their November 21, 2025 show with an opera story and a brief look at NVIDIA.
1:02ENMatthew Berman· 31 oct 2025Inside a Cerebras Data Center in Oklahoma CityMatthew Berman · Forward FutureMatthew Berman tours the facility and explains its wafer-scale chips, racks and cooling system.
14:07ENMatthew Berman· 23 oct 2025Inside Cerebras’s Oklahoma City AI Data CenterMatthew Berman, Andrew Feldman, Billy Wooten · Forward FutureMatthew Berman tours the facility with Cerebras CEO Andrew Feldman and Scale Data Centers COO Billy Wooten, exploring wafer-scale chips, liquid cooling and backup power. Their performance and expansion figures are presented as company claims from 2025.
0:58ENMatthew Berman· 26 sept 2025Microsoft’s Nebius GPU Infrastructure AgreementMatthew Berman · Forward FutureIn a sponsored video, Matthew Berman discusses a 2025 infrastructure agreement and Nebius’s AI services.
0:59ENMatthew Berman· 10 jun 2025Satya Nadella on AI's Energy Use and Social PermissionMatthew Berman, Satya Nadella · Forward FutureIn a short interview excerpt, Microsoft's CEO argues that the technology industry must deliver broad benefits as its energy demand grows.
0:36ENMatthew Berman· 2 may 2025How Much Electricity Will AI Data Centers Use?Matthew Berman, Eric Schmidt · Forward FutureMatthew Berman highlights Eric Schmidt's congressional testimony and asks about AI's power demand. The dramatic 99% figure lacks a specified time frame and geographic scope in the quoted testimony.
7:57ENMatthew Berman· 22 ene 2025Stargate’s 2025 Announcement and the OpenAI–Microsoft PartnershipMatthew Berman · Forward FutureMatthew Berman reviews the planned US AI infrastructure project and a contemporaneous change to compute arrangements.
6:16ENMatthew Berman· 8 dic 2024Running Stable Diffusion 3.5 with ComfyUI on a Cloud GPUMatthew Berman · Forward FutureIn a Vultr-sponsored 2024 tutorial, Matthew Berman sets up a GPU instance and generates images with ComfyUI. Licensing, security, and prices require attention beyond the demonstration.
1:00ENMatthew Berman· 31 oct 2024AI Growth and the Pressure on Electricity InfrastructureMatthew Berman · Forward FutureMatthew Berman considers how the power demands of AI and data centers could affect grids, emissions and competition for resources.
0:44ENMatthew Berman· 29 ago 2024NVIDIA Adds Multi-LoRA Serving to Its RTX AI ToolkitMatthew Berman · Forward FutureIn an NVIDIA-partnered video, Matthew Berman describes using multiple adapters with one base model and a vendor-reported throughput gain.
7:43ENMatthew Berman· 17 jul 2024How to Run STORM for AI-Assisted ResearchMatthew Berman · Forward FutureMatthew Berman demonstrates Stanford’s research tool, from its 2024 local setup to a cited article about dogs. The interface runs locally, while his demonstration relies on external AI and search APIs.Cargar másMostrando 24 de 39