Deep Dives
247 articles
Deep Dive into AI Agent Skill Design: …
Deep Dive into AI Agent Skill Design: Engineering Practices from Anthropic and Perplexity
A deep dive into Skill design philosophy from Anthropic's Claude Code team and Perplexity's Agent team, covering the Tax Test, Gotchas Flywheel, progressive disclosure, and Eval-First practices for building high-quality AI Agent skill systems.
Deep Dive into OpenAI's Official GPT-5…
Deep Dive into OpenAI's Official GPT-5.6 Prompting Guide: The Shift from Manual to Automatic
A deep dive into OpenAI's official GPT-5.6 Sol prompting guide: conciseness-first, outcome-oriented design, autonomy boundaries, tool routing, and reasoning intensity tuning.
Deep DivesDeep Dive into How OpenClaw (Open-Source Crayfish) AI Agent Works
Deep analysis of OpenClaw AI Agent internals: System Prompt, tool calling, SubAgents, Skill system, memory, and Context Engineering explained.
Deep DivesDemystifying Transformer: A Word-Continuation Function, Deconstructed
Understand Transformer through the lens of word continuation. Breaking down language generation into Embedding, Transformer Block, and Probability output modules for intuitive understanding.
Deep DivesFive Core Differences Between Claude Code and Regular AI Chat
A detailed comparison of Claude Code vs regular AI chat across five dimensions: interaction, context understanding, execution, memory, and tool integration.
Deep DivesMCP and A2A Protocols Explained: The USB Era of Agent Interoperability
A deep dive into MCP (Model Context Protocol) and A2A (Agent-to-Agent Protocol) — their architecture, core features, and how they work together to enable plug-and-play agent interoperability.
Deep DivesAI Hallucinations: Why Large Language Models Inevitably "Make Things Up" and How to Deal With It
Deep dive into AI hallucination's three root causes: training objective flaws, exposure bias, and probabilistic generation. Covers classification and practical mitigation strategies including RAG.
Deep DivesThe "Worse is Better" Philosophy of Large Model Design: Why Simple and Brutal Beats Refined and Complex
Analyzing the "worse is better" philosophy in large model architecture: why DeepSeek V4 dropped N-gram, why Transformer dominates AI, and three iron laws of simple, efficient model design.
Deep DivesComplete Guide to LLM Training: Pre-training, SFT Fine-tuning, and Preference Alignment Explained
Complete guide to the three core LLM training stages: pre-training, supervised fine-tuning (SFT), and preference alignment (DPO/PPO), covering LoRA, distillation, quantization, and pruning.
Deep DivesMCP (Model Context Protocol): Solving the Three Core Pain Points of AI Tool Calling
Deep dive into how MCP (Model Context Protocol) solves three core pain points of Tool Calling: verbose descriptions, unstable invocations, and lack of unified standards.
Deep DivesMCP Protocol Explained: The Unified Standard and Complete Workflow for LLM Tool Calling
Deep dive into MCP (Model Context Protocol): core concepts, role definitions, and complete workflow. Learn how MCP Server, Client, and Host work together to standardize LLM tool calling.
Deep DivesDeep Dive into Pi's Swarm System: A Biology-Inspired Multi-Agent AI Programming Architecture
Deep dive into Pi's swarm system architecture (26K GitHub stars): scout, worker, and soldier ant roles, pheromone communication, adaptive concurrency control, and how multi-agent collaboration revolutionizes AI programming.
Deep DivesDeep Dive into How Claude Code Works: A New Programming Paradigm Driven by the Agent Loop
Deep dive into how Claude Code works, including the Agentic Loop, automatic context compaction, tool calling, and permission modes that power autonomous AI programming.
Deep DivesDeep Dive into Hermes Agent Self-Evolution: The GIPA Algorithm and Engineering Practice
Deep analysis of NousResearch's Hermes Agent Self Evolution project: GIPA genetic Pareto prompt evolution algorithm, six-step optimization loop, and five guardrail mechanisms for real-world Agent self-evolution.
Deep DivesHow Claude Code Works: Inside the Agentic Programming Tool
Deep dive into Claude Code's core mechanisms including tool calling, agentic search, memory systems, and MCP protocol extensions. Learn how this CLI agent tool autonomously plans and executes complex development tasks.
Deep DivesGetting Started with Claude Code: Three Core Capabilities and Usage Guide
A deep dive into Claude Code's core capabilities: understanding codebases, autonomously executing commands, and searching the web. Learn key concepts like context windows and permission control.
The Birth of General Relativity: How I…
The Birth of General Relativity: How Intuition, Knowledge, and Critique Forge Scientific Genius
Exploring how Einstein created general relativity through the fusion of intuitive sparks, deep knowledge, and rigorous self-critique—insights from Lex Fridman's conversation with physicist Don Lincoln.
Deep DivesAI Persona Distillation for Coding: Five Personalities Write Five Different Tetris Games
Using Claude Code with DeepSeek, persona distillation makes AI code as Kardashian, Musk, a Trisolaran, and Trump — proving personality settings dramatically change coding style and output.
Where Did the Antimatter Go? The Most …
Where Did the Antimatter Go? The Most Profound Unsolved Mystery of the Universe
The Big Bang should have produced equal matter and antimatter, yet antimatter nearly vanished. Explore antimatter's discovery, CERN experiments, production challenges, and the matter-antimatter asymmetry puzzle.
What Exactly Is Dark Matter? A Deep Di…
What Exactly Is Dark Matter? A Deep Dive from a Particle Physicist
Dark matter makes up 83% of all matter in the universe, yet has never been directly detected. This article examines key evidence from galaxy rotation curves, the Bullet Cluster, and Dragonfly galaxies, along with three detection approaches and current research challenges.