Author

Tencent Technical Engineering

Official account of Tencent Technology. A platform for publishing and analyzing Tencent's technological innovations and cutting-edge developments.

112

Articles

Likes

380

Views

Comments

Latest from Tencent Technical Engineering

100 recent articles max

Tencent Technical Engineering

Apr 9, 2025 · Artificial Intelligence

Discussion on Model Context Protocol (MCP) and Its Potential Applications

The discussion introduces the Model Context Protocol (MCP) as an open‑source framework that repositions AI from a peripheral add‑on to the central “brain” of software, allowing AI‑first integration with business APIs, reducing rewrites, unifying user interfaces, and promising a rapid open‑source surge that could reshape development, production, and decentralized ecosystems.

AI integrationMCPModel Context Protocol

0 likes · 7 min read

Discussion on Model Context Protocol (MCP) and Its Potential Applications

Tencent Technical Engineering

Apr 7, 2025 · Cloud Native

Deploying MCP Server on Serverless Cloud Functions with Cube Secure Containers

The article explains how to deploy a Model Context Protocol (MCP) server—illustrated with a Python weather‑query example—on Tencent Cloud Function using either a Docker image or direct code upload, leverages Cube’s high‑security lightweight containers for fast start‑up, and highlights serverless benefits such as automatic scaling, cost efficiency, and simplified operations compared with Kubernetes for AI agents and tool integration.

Cloud FunctionsCube Secure ContainerDeployment

0 likes · 21 min read

Deploying MCP Server on Serverless Cloud Functions with Cube Secure Containers

Tencent Technical Engineering

Mar 31, 2025 · Artificial Intelligence

Step-by-Step Guide to Local Training of DeepSeek R1 on Multi‑GPU A100 Systems

This step‑by‑step tutorial shows how to set up CUDA 12.4, install required packages, prepare a JSON dataset and custom reward, troubleshoot out‑of‑memory errors, and launch DeepSeek R1 training on an 8‑GPU A100 cluster using Accelerate, Deepspeed zero‑3 and vLLM configurations.

A100CUDADeepSeek

0 likes · 9 min read

Step-by-Step Guide to Local Training of DeepSeek R1 on Multi‑GPU A100 Systems

Tencent Technical Engineering

Mar 28, 2025 · Artificial Intelligence

Chat‑Style Programming with Cursor: Practices, Insights, and Tips

The article explores Cursor’s chat‑style programming paradigm—highlighting its natural‑language coding, rapid iteration, and AI‑assisted workflow—while offering communication strategies, a reverse‑Feynman learning method, divide‑and‑conquer tactics, the Model Context Protocol, ten practical tips, and a vision of human‑AI hybrid engineers achieving flow and redefining software value.

AI programmingChat-based codingCursor tool

0 likes · 13 min read

Chat‑Style Programming with Cursor: Practices, Insights, and Tips

Tencent Technical Engineering

Mar 27, 2025 · Information Security

AI Programming Assistants Can Be Hijacked: Configuration File Poisoning and Security Risks

AI programming assistants such as GitHub Copilot and Cursor can be hijacked through poisoned configuration files that hide malicious prompts using invisible Unicode characters, exposing developers to risks like data leakage, DDoS, cryptomining and trojan injection, so they must avoid unknown configs, sandbox generated code, and employ static analysis and AI audits to mitigate threats.

AI securitycode poisoningconfiguration files

0 likes · 12 min read

AI Programming Assistants Can Be Hijacked: Configuration File Poisoning and Security Risks

Tencent Technical Engineering

Mar 24, 2025 · Fundamentals

Understanding V8 Garbage Collection: Scavenger and Mark‑and‑Sweep Algorithms

V8’s garbage collector splits memory into young and old generations, using a fast Scavenger minor‑GC that marks live objects, evacuates them via semi‑space copying, and updates pointers with write barriers, while a concurrent mark‑and‑sweep major‑GC employs three‑color marking, black allocation, sweeping and optional parallel compaction, with adaptive triggering based on heap usage.

Garbage CollectionJavaScriptMark-and-Sweep

0 likes · 30 min read

Understanding V8 Garbage Collection: Scavenger and Mark‑and‑Sweep Algorithms

Tencent Technical Engineering

Mar 21, 2025 · Fundamentals

Fundamentals of GPU Architecture and Programming

The article explains GPU fundamentals—from the end of Dennard scaling and why GPUs excel in parallel throughput, through CUDA programming basics like the SAXPY kernel and SIMT versus SIMD execution, to the evolution of the SIMT stack, modern scheduling, and a three‑step core architecture design.

CUDAGPUGPU programming

0 likes · 42 min read

Fundamentals of GPU Architecture and Programming

Tencent Technical Engineering

Mar 19, 2025 · Information Security

AI Programming Security Risks and Countermeasures

As AI tools soon generate the majority of software, they dramatically amplify hidden security risks—such as hard‑coded secrets, XXE, directory traversal, and privilege escalation—requiring zero‑trust scanning, secret interception, command filtering, privilege‑fuse safeguards, and AI‑native semantic analysis to protect the modern code supply chain.

AI programmingAI securitySoftware Security

0 likes · 9 min read

AI Programming Security Risks and Countermeasures

Tencent Technical Engineering

Mar 17, 2025 · Artificial Intelligence

Building a License Approval System with Cursor AI: A Low‑Effort Full‑Stack Demo

The article demonstrates how, with Cursor’s AI‑assisted coding and its YOLO mode, a developer can rapidly build a full‑stack license‑approval system—Vue 3 front‑end, Go/Gin back‑end, JWT authentication, MySQL storage—in under a day of effort, highlighting practical tips, limitations, and the broader potential for low‑code creation.

AI programmingCursorLow‑code

0 likes · 11 min read

Building a License Approval System with Cursor AI: A Low‑Effort Full‑Stack Demo

Tencent Technical Engineering

Mar 10, 2025 · Artificial Intelligence

How Non‑AI Developers Can Build LLM Apps: Prompt Engineering, RAG, and Function Calling Explained

This guide shows non‑AI developers how to create large‑model applications by mastering prompt engineering, multi‑turn interactions, Retrieval‑Augmented Generation, function calling, and AI‑Agent integration, with practical code examples, tool design patterns, and deployment tips.

AI agentEmbeddingFunction Calling

0 likes · 48 min read

How Non‑AI Developers Can Build LLM Apps: Prompt Engineering, RAG, and Function Calling Explained