LLMs Portfolio
Get to know the most popular LLMs and their families
My latests articles
Read more about LLMs, AI and software development
Running LLMs Locally
A comprehensive guide to running large language models on your own hardware, covering concepts, architectures, and decision frameworks.
ML and DL frameworks
A software engineer's guide to understanding and choosing machine learning and deep learning frameworks like TensorFlow, PyTorch, scikit-learn, and more.
GitHub models
An in-depth overview of GitHub Models feature available now for all developers.
AI certificates
A deep dive into modern AI certifications for developers and their real-world value in building production AI systems.
Web development and AI news
Stay updated with the latest news in web development and AI.
Web development
PinMe: Free CLI Tool for Static Site Deployment
A free command-line tool that allows developers to deploy static sites quickly and keep them online without ongoing costs or maintenance.
Server-Side Support for MCP in Next.js
Updates and guides on implementing Model Context Protocol (MCP) server-side within Next.js applications, enabling AI assistant integration.
jsonrepair: Repair Invalid JSON Documents
A tool and library for fixing invalid JSON, useful for handling non-compliant data sources like LLM outputs.
Artificial intelligence
Google rolls out AI Mode in Search and Veo 3 globally
Google has made its Gemini-powered AI Mode the default search experience in the U.S. and expanded the availability of its Veo 3 video generation model globally, signaling a major push to integrate AI across its core products.
Perplexity introduces Comet, an AI-first web browser
Perplexity has launched Comet, a browser embedding a live AI assistant that reads pages, answers questions, and performs tasks directly within the interface, aiming to integrate AI more deeply into web navigation.
xAI launches Grok 4 and Grok 4 Heavy models
Elon Musk's xAI has released Grok 4 and Grok 4 Heavy, new high-performance models claiming state-of-the-art benchmark scores, featuring multi-agent capabilities and larger context windows, available via subscription and API.
