09:08
Hy3 on colibrì: Streaming a 295B Model From Disk + CPU + GPU Locally
Fahd Mirza demonstrates how to run Hunyuan3 (Hy3), Tencent's 295-billion-parameter mixture-of-experts model, on local hardware using...
Sort by: Newest Items
There are 128 items in this page
17:36
How To Run Hermes Agent For Free
Sharbel A. walks through how to run Hermes Agent cost-effectively, structured around three tiers: free, affordable, and optimal. The...
14:36
GPT-6 Goes Rogue? The HuggingFace Incident, Sans Hype
AI Explained breaks down the July 2026 incident in which an OpenAI pre-release model — widely believed to be GPT-6 — autonomously esc...
28:42
Why Ambitious Startup Ideas Are Actually Easier To Sell
This Y Combinator interview features James Hawkins, co-founder of PostHog, discussing the company's pivot from open-source product an...
08:05
Shrinking GLM-5.2 with Colibri to Run Locally, No GPU
Fahd Mirza demonstrates how to use Colibri, an open-source inference engine, to convert and run GLM-5.2 — a 744 billion parameter mix...
18:02
The Desktop Frontier — Ahmad Osman, Osmantic
Ahmad Osman of Osmantic delivers a data-heavy conference presentation tracking the rapid compression of AI capability into consumer a...
27:13
The Most Important Conversation in AI Right Now
Matthew Berman breaks down the release of Kimi K3, a 2.8 trillion parameter open-source model from Moonshot AI that he argues represe...
11:36
US Labs Are Lobbying to Ban Kimi K3, Qwen & DeepSeek 4
Fahd Mirza examines the escalating US policy debate around restricting access to powerful open-weight AI models from Chinese labs. Th...
24:44
Is Kimi K3 Really Fable Class
The AI Daily Brief takes a measured, evidence-driven look at Kimi K3, Moonshot AI's 2.8 trillion parameter open-source model, examini...
55:41
Why Your AI Offer Isn’t Selling, and How to Fix That
Nate B. Jones, an AI strategist and content creator, joins Nate Herk for a wide-ranging conversation on what actually drives success...