Author

Code Mala Tang

Read source code together, write articles together, and enjoy spicy hot pot together.

521

Articles

Likes

4.7k

Views

Comments

Latest from Code Mala Tang

100 recent articles max

Code Mala Tang

Jun 20, 2026 · Artificial Intelligence

How a 9K‑Star MCP Server Lets Claude Code Scan Millions of Lines in Milliseconds

The codebase-memory-mcp tool builds a tree‑sitter‑based knowledge graph of a codebase, enabling sub‑millisecond queries, 120× token savings, zero‑dependency deployment, cross‑agent sharing, and reproducible benchmarks that show higher answer quality and far lower resource usage than traditional file‑by‑file grep approaches.

Code IndexingCoding AgentsKnowledge Graph

0 likes · 12 min read

How a 9K‑Star MCP Server Lets Claude Code Scan Millions of Lines in Milliseconds

Code Mala Tang

Jun 19, 2026 · Artificial Intelligence

Five Skeptical Questions About RTK’s Token Compression Claims

The article critically examines RTK’s token‑compression promises, exposing misleading savings metrics, silent‑failure bugs, missing task‑success benchmarks, its status as a fragile feature rather than a product, and the brittleness of its output parser, before offering concrete guidance on when to use it.

CLI output parsingLLM agentsRTK

0 likes · 8 min read

Five Skeptical Questions About RTK’s Token Compression Claims

Code Mala Tang

Jun 18, 2026 · Artificial Intelligence

From Tool Calls to Real Execution: Inside Claude Code’s 43‑Tool Scheduling System

The article dissects Claude Code’s tool runtime, detailing how a unified TypeScript interface, a feature‑gated registry, a seven‑stage dispatch pipeline, and a concurrency scheduler transform model‑generated tool_use blocks into safe, parallel or serial system operations, including dynamic MCP extensions.

Claude CodeLLM Tool ExecutionMCP

0 likes · 19 min read

From Tool Calls to Real Execution: Inside Claude Code’s 43‑Tool Scheduling System

Code Mala Tang

Jun 18, 2026 · Artificial Intelligence

How Warp’s Dual‑Loop Architecture Enables Self‑Improving AI Agents

The article explains Warp founder Zach Lloyd’s practical dual‑loop system that lets AI agents automatically learn from human‑corrected feedback, continuously refining their task‑execution skills through an inner execution loop and an outer improvement loop.

AI AgentGitOpsWarp

0 likes · 10 min read

How Warp’s Dual‑Loop Architecture Enables Self‑Improving AI Agents

Code Mala Tang

Jun 16, 2026 · Industry Insights

GitHub Star Inflation: Why 10,000 Stars No Longer Impress

The article analyzes how GitHub star counts have inflated—especially for AI tools—showing that a 20,000‑star threshold that once guaranteed a top‑10 spot now falls short, and explains why stars are becoming a noisy attention metric rather than a reliable quality indicator.

AIGitHubOpen Source

0 likes · 13 min read

GitHub Star Inflation: Why 10,000 Stars No Longer Impress

Code Mala Tang

Jun 16, 2026 · Industry Insights

Chrome Pulls the Last Nail on MV2: Ad‑Blocker Era Ends, MV3 Changes & Migration Paths

Chrome versions 150 and 151 will finally remove all Manifest V2 support, ending the decade‑long ad‑blocking extension model; the article explains Google’s reasons, the technical differences between MV2 and MV3, the impact on uBlock Origin, and migration options including Firefox and alternative architectures.

Ad blockersChromeManifest V2

0 likes · 9 min read

Chrome Pulls the Last Nail on MV2: Ad‑Blocker Era Ends, MV3 Changes & Migration Paths

Code Mala Tang

Jun 15, 2026 · Artificial Intelligence

Nadella’s AI Test: What Remains When You Swap Out Your Core Model?

Satya Nadella challenges enterprises to replace their underlying large‑language model and see what AI capabilities truly stay in‑house, revealing that most assets are rented while only user interaction data and internal logs constitute genuine token capital.

AI StrategyEnterprise AImodel swapping

0 likes · 9 min read

Nadella’s AI Test: What Remains When You Swap Out Your Core Model?

Code Mala Tang

Jun 13, 2026 · Artificial Intelligence

When Claude Went Offline, a Chinese Model Picked Up the Slack

The sudden suspension of Anthropic's Claude models sparked a surge of discussion in China's AI community, leading to the rapid release of GLM‑5.2, whose extended context window, coding‑plan subscription, and mixed performance on engineering tasks provide developers with a detailed comparative analysis against Claude Opus 4.8.

AI model evaluationClaude OpusCoding Agents

0 likes · 10 min read

When Claude Went Offline, a Chinese Model Picked Up the Slack

Code Mala Tang

Jun 12, 2026 · Industry Insights

Why AI Vendors Claim 80% of Code Is AI‑Generated—and What the Numbers Really Mean

The article dissects AI vendors' bold claims that 80% of code is AI‑written, reveals how these volume metrics replace dismissed pseudo‑indicators, contrasts them with mixed research findings on productivity and quality, and warns that such numbers can drive budgets, OKRs, and even layoffs.

AI adoptionAI code generationdeveloper productivity

0 likes · 12 min read

Why AI Vendors Claim 80% of Code Is AI‑Generated—and What the Numbers Really Mean

Code Mala Tang

Jun 12, 2026 · Artificial Intelligence

Loop Engineering: When AI Coding’s Bottleneck Shifts from Prompt to Loop

The article argues that single‑call AI agents have hit their performance ceiling and that the next frontier, called Loop Engineering, moves the heavy lifting from prompt design to automated, self‑checking loops, while outlining real‑world attempts, core components, and practical limitations.

AI AgentsAnthropicCodex

0 likes · 17 min read

Loop Engineering: When AI Coding’s Bottleneck Shifts from Prompt to Loop