Author

Code Mala Tang

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

517

Articles

Likes

3.9k

Views

Comments

Latest from Code Mala Tang

100 recent articles max

Code Mala Tang

Aug 18, 2026 · Artificial Intelligence

How Claude’s Text Watermark Works: Anthropic’s Technical Explanation

Anthropic explains that Claude’s text watermark, derived from DeepMind’s SynthID‑Text and Scott Aaronson’s 2022 concept, alters the model’s token‑selection randomness with a secret key to embed statistical traces without degrading quality, while outlining its detection limits, code‑generation nuances, privacy properties, and industry rollout.

AI model detectionAnthropicClaude

0 likes · 6 min read

How Claude’s Text Watermark Works: Anthropic’s Technical Explanation

Code Mala Tang

Aug 3, 2026 · Backend Development

From Missing dingtalkid to One‑Click Agent: Building DingTalk Robot Jump Links

This guide explains how to capture the hidden $:LWCP_v1:$‑prefixed dingtalkid from DingTalk robot callbacks using a minimal Python HTTP service, then construct a dingtalk://jump‑robot link that pre‑fills a query, enabling users to launch an internal Agent with a single click.

CallbackDingTalkPython

0 likes · 12 min read

From Missing dingtalkid to One‑Click Agent: Building DingTalk Robot Jump Links

Code Mala Tang

Jul 28, 2026 · Cloud Native

What’s New in MCP Protocol’s Fifth Major Release (2026‑07‑28)?

The MCP protocol’s fifth major version switches from a stateful bidirectional model to a stateless request/response design, adding new headers, auth hardening, deprecating legacy features, updating SDKs, and gaining broad cloud and tool support, while outlining migration steps for production users.

MCPMigrationSDK

0 likes · 5 min read

What’s New in MCP Protocol’s Fifth Major Release (2026‑07‑28)?

Code Mala Tang

Jul 16, 2026 · Artificial Intelligence

How Hermes Agent’s Self‑Evolution Framework Works: DSPy Diagnoses, GEPA Evaluates

The article dissects the open‑source hermes‑agent‑self‑evolution repository, explaining how DSPy leverages large‑model APIs to diagnose skill failures and rewrite SKILL.md, while GEPA orchestrates mutation, evaluation, and Pareto‑based selection to iteratively improve Hermes Agent skills offline.

AI agentsDSPyGEPA

0 likes · 11 min read

How Hermes Agent’s Self‑Evolution Framework Works: DSPy Diagnoses, GEPA Evaluates

Code Mala Tang

Jul 9, 2026 · Artificial Intelligence

Writing Effective Agent Skills: Human‑Crafted Boost +16.2 pp, AI‑Generated Drop –1.3 pp

An empirical benchmark of 8,408 runs across 84 tasks shows that manually designed Agent Skills improve performance by up to 16.2 percentage points, while AI‑generated skills can hurt results, and distills six actionable conclusions for crafting useful, focused, and test‑validated skills.

AI agentsAgent SkillsDomain Adaptation

0 likes · 7 min read

Writing Effective Agent Skills: Human‑Crafted Boost +16.2 pp, AI‑Generated Drop –1.3 pp

Code Mala Tang

Jul 4, 2026 · Artificial Intelligence

How an AI Assistant Self‑Learns Skills and Tops GitHub Stars in 60 Days

In just 60 days the OpenClaw AI assistant, which writes and refines its own skills on a local laptop, amassed over 250,000 GitHub stars—outpacing React and Linux—while offering a self‑improving, extensible agent framework and highlighting associated security considerations.

AI agentsLocal AIOpenClaw

0 likes · 12 min read

How an AI Assistant Self‑Learns Skills and Tops GitHub Stars in 60 Days

Code Mala Tang

Jul 3, 2026 · Frontend Development

From Page Tweaker to AI Architect: The Emerging Front‑End Large‑Model Career Path

The article analyzes 2026 hiring trends that show traditional front‑end demand falling while AI‑enabled front‑end engineers earn 40% more, outlines a four‑layer capability pyramid, recommends a modern tech stack, and provides a concrete roadmap from junior to senior AI‑focused front‑end roles.

AIRAGWebGPU

0 likes · 9 min read

From Page Tweaker to AI Architect: The Emerging Front‑End Large‑Model Career Path

Code Mala Tang

Jul 2, 2026 · Artificial Intelligence

What Do AI Buzzwords Like LLM, Agent, and Skill Really Mean?

The article demystifies common AI terminology—LLM, Token, Context, Prompt, Tool, MCP, Agent, and Agent Skill—by explaining each concept, how they interrelate, and why understanding this chain clarifies the operation of modern AI products.

AI conceptsAgentLLM

0 likes · 11 min read

What Do AI Buzzwords Like LLM, Agent, and Skill Really Mean?

Code Mala Tang

Jul 1, 2026 · Artificial Intelligence

Anthropic Launches Claude Science: AI Workbench Tying 60+ Scientific Databases

Claude Science, Anthropic’s new AI workbench for scientific research, embeds the existing Claude model (including Opus 4.8) into a unified interface that links over 60 databases, supports local macOS/Linux execution, offers reproducible agent‑generated analyses, and positions itself against OpenAI’s GPT‑Rosalind by focusing on workflow integration rather than specialized model training.

AI workbenchAnthropicClaude Science

0 likes · 7 min read

Anthropic Launches Claude Science: AI Workbench Tying 60+ Scientific Databases

Code Mala Tang

Jun 30, 2026 · Operations

Turning Cross‑Project Prompts into a Structured AI Workflow with OpenSpec

The article analyzes the OpenSpec requirement‑pipeline workflow (v0.3.0), showing how a five‑step process—clarify, split, confirm, execute, wrap‑up—turns vague multi‑project requirements into a disciplined AI‑driven automation pipeline, while highlighting configuration details, suitable team contexts, common pitfalls, and practical improvements.

AI WorkflowAutomationOpenSpec

0 likes · 15 min read

Turning Cross‑Project Prompts into a Structured AI Workflow with OpenSpec