Mamerto Fabian (@mamertofabian) 's Twitter Profile
Mamerto Fabian

@mamertofabian

Founder @Codefrost | AI Development Consultant | Creator of AI-Driven Coder

Helping people build & launch AI-powered apps

🎥 youtube.com/@aidrivencoder

ID: 27407249

linkhttps://codefrost.dev calendar_today29-03-2009 10:23:50

517 Tweet

91 Takipçi

145 Takip Edilen

Mamerto Fabian (@mamertofabian) 's Twitter Profile Photo

🔐 Finally! Import PRIVATE GitHub repos into bolt.new Watch how to: 🞄 Set up the free Chrome extension 🞄 Import private repos securely 🞄 Push changes back to GitHub 🞄 Integrate with @windsurf for a complete dev workflow Get coding: youtu.be/d9NqXRoroi0

Mamerto Fabian (@mamertofabian) 's Twitter Profile Photo

🔥 Stuck in an endless AI development fixing loop? Learn how to rescue your broken project using GitHub's web interface - no command line needed! Perfect for: - Bolt new users - AI developers - Anyone struggling with broken commits Watch the tutorial: youtu.be/9G1N5ClHGMc

Mamerto Fabian (@mamertofabian) 's Twitter Profile Photo

🔥 Just dropped: Want to cut your AI token usage in HALF? My latest video shows 5 game-changing Roo Code features, including a simple setting that reduces system prompt tokens by 50%! Plus: • Custom prompt modes • Advanced API configs • System Prompt optimization Watch

Mamerto Fabian (@mamertofabian) 's Twitter Profile Photo

🚀 New Tutorial: Deploy your AI-built projects to GitHub Pages - right from your browser! No terminal needed. Free hosting. Custom domains. Perfect for Bolt projects and other AI dev tools. Watch here: youtu.be/QQHA2pU-Rm4 #AIDevTools #WebDev #GitHubPages

DeepSeek (@deepseek_ai) 's Twitter Profile Photo

🚀 Day 1 of #OpenSourceWeek: FlashMLA Honored to share FlashMLA - our efficient MLA decoding kernel for Hopper GPUs, optimized for variable-length sequences and now in production. ✅ BF16 support ✅ Paged KV cache (block size 64) ⚡ 3000 GB/s memory-bound & 580 TFLOPS

Alex Albert (@alexalbert__) 's Twitter Profile Photo

Last year, Claude was in the assist phase. In 2025, Claude will do hours of expert-level work independently and collaborate alongside you. By 2027, we expect Claude to find breakthrough solutions to problems that would've taken teams years to solve.

Last year, Claude was in the assist phase.

In 2025, Claude will do hours of expert-level work independently and collaborate alongside you.

By 2027, we expect Claude to find breakthrough solutions to problems that would've taken teams years to solve.
Mamerto Fabian (@mamertofabian) 's Twitter Profile Photo

🚀 Cursor 0.50 just dropped! Major updates include: • Simplified request-based pricing model • Max Mode now available for all top models • New Background Agent for parallel task execution • @ folders support for entire codebase context • Refreshed Inline Edit with new

Mamerto Fabian (@mamertofabian) 's Twitter Profile Photo

🚀 MAID Runner is now live! Stop AI from breaking your code with validation that actually works. 📦 pip install maid-runner ⭐ github.com/mamertofabian/… Episode 0 explains why AI instructions fail + shows the solution ↓ youtube.com/watch?v=0a9ys-… #BuildInPublic #Cursor #Claude

Mamerto Fabian (@mamertofabian) 's Twitter Profile Photo

🎯 MAID Runner explained: Step-by-step by building a production-ready MCP server with Claude Code. Tame powerful AI models using MAID Runner! ▶️ youtube.com/watch?v=A4_6zq… #vibecoding #claudecode

Mamerto Fabian (@mamertofabian) 's Twitter Profile Photo

🚀 New Tutorial: MAID Runner Methodology with Claude Code Learn AI-assisted development done RIGHT: ✅ Manifest-driven workflow ✅ Behavioral tests BEFORE coding ✅ Custom Claude Code sub-agents ✅ Parallel implementation I demonstrate the complete MAID workflow - from spike