MCP vs A2A: Everything you need to know
Am I a bit late to talk about MCP and A2A protocols? I hope not! Both have been all over the internet,
GPT-4.1 vs. Deepseek v3 vs. Sonnet 3.7 vs. GPT-4.5
GPT 4.1 is here. As many speculated, the mysterious Quasar Alpha on OpenRouter was GPT-4.1, and Optimus Alpha was GPT-4.1 mini. And
Notes on Llama 4: The Hits, the Misses, and the Disasters
The Llama 4 is here, and this time, the Llama family has three different models: Llama 4 Scout, Maverick, and Behemoth. While
Gemini 2.5 Pro vs. Claude 3.7 Sonnet (thinking) vs. Grok 3 (think)
Google dropped its best-ever creation, Gemini 2.5 Pro Experimental, on March 25. It is a stupidly incredible reasoning model shining on every
Deepseek v3 0324: Finally, the Sonnet 3.5 at Home
Deepseek v3 o324, a new checkpoint, has been released by Deepseek in silence, with no marketing or hype, just a tweet, a
What is Model Context Protocol (MCP): Explained
Introduction Anthropic released MCP (Model Context Protocol) in November 2024. The developer community initially responded positively, yet few realized its full potential.
Claude 3.7 Sonnet thinking vs. Deepseek r1
So, Anthropic finally broke the silence and released Claude 3.7 Sonnet, a hybrid model that can think step-by-step like a thinking model
OpenAI o3-mini vs o1 vs Deepseek r1
OpenAI launched its latest model, the o3-mini, last Friday. It is the first member of the o3 family of models. There are
Crypto-Kit: Build AI-powered Web3 Automation
AI and crypto are two revolutionary technologies of the 21st century. They are redefining how we process information and transact value, and
Notes on the new Deepseek r1
Before anything, let’s bow to Richard Sutton; he was so early for this. Pure RL, neither Monte-Carlo tree search (MCTS) nor Process
AI SDR-Kit: Build AI sales agents with 60+ app integrations
AI is eating the world. To paraphrase Marc Andreessen’s famous line, “Software is eating the world.” We’re living in an exciting era.
Notes on the new Deepseek v3
Deepseek released their flagship model, v3, a 607B mixture-of-experts model with 37B active parameters. Currently, it is the best open-source model, beating