10:33
Mellum2: JetBrains’ New Coding Model – vLLM + MCP Tool Use Locally
JetBrains has released Mellum 2, a 12-billion-parameter mixture-of-experts coding model that runs at the compute cost of a 2.5-billio...
Sort by: Newest Items
There are 402 items in this page
06:01
Run Google’s newest 12B AI on a phone? Yes, it’s possible!
The Alphastack channel walks through a custom cross-platform app that runs Google's Gemma 4 12B multimodal model entirely on-device —...
09:18
I’m working on a self hosting cli tool
Web Dev Cody shares an early but functional demo of \"Launchpad,\" an open-source self-hosting CLI tool he's building as a developer-...
18:04
Claude Plans, Gemini Designs: The Workflow to Build BEAUTIFUL Frontends
Cole Medin presents a complete, open-source workflow that mixes two AI providers — Google's Gemini 3.5 Flash for front-end UI design...
12:27
Nemotron 3 Ultra – NVIDIA’s Most Powerful Open Model – Long Running Agents
NVIDIA has released Nemotron Ultra, its largest open model to date at 550 billion total parameters—with only 55 billion active at inf...
30:20
Agentic AI Trading For Beginners: A New Money Making Era Is Here
The All About AI channel explores how beginners can combine agentic AI with financial trading across cryptocurrency exchanges and pre...
20:36
I cloned myself with Gemini Omni in 15 minutes (and it’s terrifyingly good)
In this episode of How I AI, host Claire walks through a live, end-to-end experiment using Google Flow and the Gemini Omni video gene...
12:22
I use this Claude Skill to edit my videos with no code
Stephanie Nyarko shows how she built a fully automated video editing workflow inside Claude using a custom skill — no coding required...
14:00
Building a Agentic AI Trading Heartbeat That Works
This video from the All About AI channel walks through a working agentic trading system built around a 'heartbeat' architecture: a li...
25:53
Ghost AI let’s AI Agents build disposable worlds
Wes Roth introduces Ghost AI (ghost.build), a tool that creates isolated, disposable PostgreSQL database copies on demand—solving one...
09:39
Step 3.7 Flash – 198B Open Source Model That Does Everything; Does it Really?
Step 3.7 Flash is a 198 billion parameter sparse mixture-of-experts model from Step One, activating only 11 billion parameters per to...
08:53
LFM2.5-8B-A1B: Local Agentic AI with Multilingual Support Tested
LFM2.5-8B-A1B is Liquid AI's latest open-weight model — an 8.3 billion parameter mixture-of-experts architecture that activates only...
08:38
My AI Coding Workflow — Everything I Use Now (for peak performance)
Edmund Yong walks through the development of new features for CreateSkills, a browser extension and custom MCP server he's building t...
12:19
I Stopped Using PowerPoint After Building This Claude Code Skill (Full Tutorial + 3 Templates)
Product builder Peter Yang walks through how he replaced PowerPoint and Google Slides entirely by building a custom /slides skill ins...
12:42
I Automated My Entire Twitter Strategy With This AI Agent
Craig Hewitt walks through building a fully autonomous Twitter content agent using Twin, an AI agent platform with built-in browser a...
10:06
DFlash Leaves Qwen Territory – Gemma 4 31B Now Runs 5x Faster with Speculative Decoding
Fahd Mirza demonstrates the first end-to-end deployment of Llama Box DFlash with Google's Gemma 4 31B model, following the merge of P...