08:12
Gemma 4 Just Got a Massive Update (Tested Live Locally)
Fahd Mirza puts Gemma 4's latest patch update under the microscope in a live session running on an Nvidia H100 with vLLM on a fresh U...
Sort by: Newest Items
There are 140 items in this page
13:39
Kimi K3: Testing Moonshot’s 2.8T Open Model without Hype
Fahd Mirza woke up at 4 AM in Sydney to put Kimi K3 through its paces the moment Moonshot AI's API went live, and the result is one o...
12:14
Ternary Bonsai 27B: Full Model, 2-Bit, Run on Phone or Laptop or GPU
Fahd Mirza runs Bonsai 27B — a 27-billion parameter open-weight model from Prism ML based on Gemma 3 27B — on an NVIDIA RTX A6000 GPU...
22:50
Most People Use AI Wrong | Here’s What They’re Missing
Creator Sharbel A. makes the case that most people misuse AI by treating it as an on-demand chatbot rather than designing role-based...
08:55
OpenLumara + Ollama: Local Agent Trying to Beat OpenClaw and Hermes
Fahd Mirza walks through the installation and live testing of OpenLumara, an open-source Python agent framework designed specifically...
28:29
Tailscale, Clearly Explained (Beginner’s Guide)
David Ondrej provides a beginner-friendly guide to Tailscale, the private networking tool built on WireGuard, framed specifically aro...
35:51
Local AI models explained: How to run a fleet of Mac Studios and GPUs at home
How I AI host Claire Vell interviews Alex Finn, who has built one of the more elaborate home AI infrastructure setups in the practiti...
19:10
How to setup a business brain (powered by Claude)
Brian Casel of Builder Methods argues that Claude's built-in Projects feature — not complex custom ingestion pipelines — has delivere...
10:03
Qwythos-9B-v2: The Looping Bug Gone – FTPO Explained + Local Testing
Fahd Mirza tests Qwythos 9B v2 (also called Qutoz) — a 9-billion-parameter fine-tune of Qwen 2 with deep chain-of-thought reasoning —...
07:14
What Does Done Even Mean? Agents and Paperclip’s Liveness Model – Dotta, Paperclip
In this AI Engineer conference talk, Dotta — creator of Paperclip — challenges one of the most deceptively simple assumptions in agen...