Channel Avatar

Zero to MVP

34K subscribers

AI that actually works — tested on real tasks, with real numbers. I'm Nick Blokhin, a software a ...


06:46
How to Make AI Videos From Scratch: 3 Prompts, 10 Minutes
05:12
Fable 5.2 — a routine update or a real step forward?
09:21
I Tried to Break DeepSeek V4.1 Flash on 6 Backend Tasks
06:15
Ripple 65B: A Chip Lab Beat Every US Open Model. I Tested It
08:35
15 Cents a Run: Are Chinese Flash Models Good Enough to Code?
08:01
I Treated AI Video Like Code. Here’s What Broke
04:09
How My MacBook Turns Into an AI Workstation
08:10
$7 vs $0.65: Opus 5.5 and MiniMax M3.1 Flash on My Go Project
05:55
Kimi K3.1 Pro Is Nearly Opus 5.5 on Paper. What About a Real Project?
07:29
Claude vs DeepSeek vs Local Qwen 3.8: Who Directs a Better AI Video Edit?
08:58
Can an Agent Make a Small Local Model Reliable?
06:01
New DeepSeek V4.1 Flash vs Claude Opus 5.5 on a 20,000-Line Project
07:08
I Forced AI to Promote My App (And It Invented Features)
06:06
Can a 1B AI Model Actually See? I Tested 29 Tasks
08:13
Claude Haiku 5.5 vs Local Qwen 3.8 27B: Is Local AI Still Worth It?
07:14
A 125B Local Model on a 16GB GPU: Fast, But Is It Smart?
07:03
No Designer, One Prompt: Opus 5.5 Made My Launch Page and Promo Video
10:03
Which Local AI Model Should You Run on a Raspberry Pi 5?
09:44
GPT-6 Sol vs Opus 5.5 — Picking My New Daily Driver
09:14
I Built a Scheduler So My Local LLMs Can Share One GPU
12:23
The Best Local LLMs You Can Run on a Normal Home Computer
02:07
Ornith 1.5 Speed on a MacBook M4 Pro — 9B and 35B
10:31
Qwen 3.8 Locally: How Much Can You Actually Trust It?
09:05
Why I Run 2–4 GB AI Models 24/7
10:16
Gemma 4 12B Coder Tested: Where Small Local Models Break
06:43
Testing Qwen 3.8 on a Real App, Not Benchmarks
09:28
Can a Small Local LLM Actually Build a Useful App?
07:15
GLM 5.2 vs Kimi K2.7 Code — Which Is Better for Coding?
06:39
Testing GLM 5.2 on Easy, Medium, and Hard Coding Tasks
06:34
Getting Started with Hermes Agent — Install, Configure, Run
03:20
Can Hermes Agent Use Claude Code? (Yes — Here's How)
12:35
Hermes + DeepSeek 4 + MiniMax 2.7: Multi-Model Coding on a ZimaBoard
06:07
Gemini 3.5 Flash First Look — Real Coding Test
03:02
From Gemma 4 Test Task to Real App: Introducing Texodus
10:35
Qwen 3.6 vs Gemma 4: I Built the Same App With Both Locally
09:19
Testing Qwen 3.6 Locally on Easy, Medium, and Hard Coding Tasks
06:26
Zed Editor + Local LLMs: Full Setup Guide with Ollama and LM Studio
03:25
How to Connect DeepSeek v4 to VS Code in 2 Minutes
08:40
DeepSeek v4 + Hermes Agent + ZimaBoard 2: My New AI Coding Setup
08:46
Hermes Agent on Raspberry Pi: Self-Improving AI in Under 8 Minutes
03:19
Claude Opus 4.7 Built My Desktop App From an Empty Folder
06:30
Claude Code + VS Code + Local LLM: The Perfect Dev Setup
08:21
Coding in VS Code with Gemma 4 and Ollama
10:03
How I Use Claude Code with Gemma 4 (Local LLMs, No API Costs)
09:09
Gemma 4 on Raspberry Pi 5: A Surprisingly Usable Local AI Setup
08:14
Gemma 4 - I Tested it on My Laptop and Desktop
02:14
I Ran a 48GB AI Coding Model Locally — Here's How Fast It Actually Is
08:19
Nemotron 3 Super: Can an 83GB Model Run on 16GB VRAM?
08:31
Qwen Coder Next Locally: Can It Replace Paid AI Models?
02:14
Rust vs Nim vs C: How Big Is Your Hello World?
09:19
Qwen 3.5 Locally: Can It Replace Paid AI Models?
04:51
Password Manager Devlog #2: Database Decryption, Entries & Saving
08:23
Why I Decided to Build My Own Password Manager
09:27
Choosing a New Color Theme for Zed Editor
05:46
Run AI Models Locally for FREE - Simple 3-Step Guide (Ollama Tutorial)
10:03
7 MCP Servers That Turn AI Into a Real Developer Assistant
08:40
What is MCP? (And Why You Must Start Using It)
03:33
3 Ways to Backup All Your GitHub Repositories
05:31
I Tested Google Antigravity’s Browser Control — How It Works
04:36
Google Antigravity: Can It Replace VS Code?