Author

JD Tech Talk

Official JD Tech public account delivering best practices and technology innovation.

398

Articles

Likes

2.6k

Views

Comments

Latest from JD Tech Talk

100 recent articles max

JD Tech Talk

Mar 3, 2026 · Mobile Development

When AI Hurts Mobile Apps: Practical Lessons on Performance, UX, and Pragmatic Design

The article examines how careless AI integration can degrade mobile app performance, cause overheating, battery drain, and poor user experience, and proposes a systematic, user‑centric approach—including device fragmentation awareness, lightweight models, graceful degradation, and edge‑cloud collaboration—to ensure AI adds value rather than harm.

AI integrationARdevice fragmentation

0 likes · 15 min read

When AI Hurts Mobile Apps: Practical Lessons on Performance, UX, and Pragmatic Design

JD Tech Talk

Mar 2, 2026 · Artificial Intelligence

How AI Agents Are Revolutionizing Insurance: Methodology, Economics, and Technical Blueprint

This article presents a comprehensive methodology for selecting AI agent scenarios, explains the economic benefits of agent deployment, details the technical architecture—including domain large models, knowledge bases, planning strategies, and RL‑based scheduling—and illustrates how these components are applied to insurance product design, pricing, fulfillment, and risk control to drive scale and profit.

Insuranceagentlarge model

0 likes · 42 min read

How AI Agents Are Revolutionizing Insurance: Methodology, Economics, and Technical Blueprint

JD Tech Talk

Feb 4, 2026 · Artificial Intelligence

How Deep Research Turns LLMs into Autonomous AI Researchers

This article explains the background, core features, underlying ReAct‑based architecture, and engineering solutions of Deep Research—a system that equips large language models with autonomous planning, long‑chain reasoning, and professional report generation to tackle complex information‑intensive tasks.

AI researchInformation RetrievalLLM

0 likes · 21 min read

How Deep Research Turns LLMs into Autonomous AI Researchers

JD Tech Talk

Jan 30, 2026 · Artificial Intelligence

How JD’s 9N‑LLM Engine Powers Scalable Generative Recommendation at Billion‑Scale

This article details JD Retail’s 9N‑LLM unified training engine, explaining the background of generative recommendation, the challenges of massive sparse and dense parameters, and the multi‑framework, multi‑hardware solutions—including efficient sample processing, large‑scale sparse embedding, dense scaling, UniAttention acceleration, and reinforcement‑learning integration—that enable industrial‑scale deployment.

AI InfrastructureGenerative RecommendationLarge‑Scale Training

0 likes · 26 min read

How JD’s 9N‑LLM Engine Powers Scalable Generative Recommendation at Billion‑Scale

JD Tech Talk

Jan 26, 2026 · Backend Development

Building a Multi‑Protocol MCP Server in TypeScript: Full Guide and Code

This article introduces a TypeScript MCP‑Server framework that simultaneously supports stdio, streamableHttp, and SSE protocols, explains its design motivations, outlines its modular architecture, provides setup and deployment instructions, and showcases key source code and usage examples.

MCPNode.jsSSE

0 likes · 9 min read

Building a Multi‑Protocol MCP Server in TypeScript: Full Guide and Code

JD Tech Talk

Jan 16, 2026 · Information Security

How to Capture Network Packets Remotely with Wireshark and rpcapd

This guide explains how to set up remote packet capture using Wireshark and the rpcapd service, covering software installation, network requirements, enabling the remote daemon, and configuring Wireshark for real‑time analysis of high‑frequency traffic on devices with limited resources.

Remote CaptureWiresharknetwork analysis

0 likes · 4 min read

How to Capture Network Packets Remotely with Wireshark and rpcapd

JD Tech Talk

Jan 15, 2026 · Artificial Intelligence

Uni-Layout: Harnessing Human Feedback for Unified Layout Generation and Evaluation

Uni-Layout introduces a unified framework that generates layouts across diverse tasks, simulates human evaluation with a novel feedback dataset, and aligns generation and assessment through dynamic margin preference optimization, achieving state‑of‑the‑art performance on multiple benchmarks.

AI designEvaluationHuman Feedback

0 likes · 11 min read

Uni-Layout: Harnessing Human Feedback for Unified Layout Generation and Evaluation

JD Tech Talk

Jan 12, 2026 · Frontend Development

Master Playwright: Fast Front‑End Automation Testing with Code Samples

This guide explains why Playwright has become essential for front‑end automation testing, walks through installing Node.js and Playwright, shows how to configure a project, provides runnable demo code, and illustrates common API calls such as GET and POST requests with detailed examples.

APIFrontend TestingNode.js

0 likes · 5 min read

Master Playwright: Fast Front‑End Automation Testing with Code Samples

JD Tech Talk

Jan 9, 2026 · Artificial Intelligence

How JoyCode Agent Scored 74.6% Pass@1 on SWE‑bench Verified with a Patch‑Test Co‑generation Loop

JoyCode Agent leverages a patch‑test co‑generation and iterative validation framework to achieve a 74.6% Pass@1 score on the SWE‑bench Verified benchmark, reducing resource consumption by 30‑50% and introducing a closed‑loop multi‑agent pipeline that integrates testing, patch generation, trajectory compression, similarity retrieval, and decision arbitration.

AICode RepairLLM

0 likes · 41 min read

How JoyCode Agent Scored 74.6% Pass@1 on SWE‑bench Verified with a Patch‑Test Co‑generation Loop

JD Tech Talk

Jan 9, 2026 · Artificial Intelligence

How JoyCode Agent Reached 74.6% Pass@1 on SWE‑bench Verified with a Patch‑Test Co‑Generation Loop

This technical report details JoyCode Agent’s end‑to‑end pipeline that couples patch generation with fail‑to‑pass and pass‑to‑pass test creation, uses trajectory compression, CSR similarity retrieval, and multi‑agent iterative retries to achieve a 74.6% Pass@1 score on the SWE‑bench Verified benchmark while cutting compute costs by 30‑50%.

AI code repairAutomated TestingMulti-Agent System

0 likes · 38 min read

How JoyCode Agent Reached 74.6% Pass@1 on SWE‑bench Verified with a Patch‑Test Co‑Generation Loop