Official account of Tencent Technology. A platform for publishing and analyzing Tencent's technological innovations and cutting-edge developments.
This article walks through the common pain points of manual PPT preparation and shows how CodeBuddy’s document‑skills PPTX skill can automate slide generation, editing, and templating through step‑by‑step installation, configuration, and practical examples, including code snippets and visual results.
This article walks through constructing a small large‑language model from the ground up, covering model architecture, tokenization methods, BPE vocabulary building, embedding, positional encoding, attention mechanisms, multi‑head attention, transformer blocks, training pipelines, inference, and sampling strategies, all with runnable Python code.
This study investigates the security performance of AI‑generated code in real‑world software projects, revealing high vulnerability rates, language‑specific adoption patterns, and evolving roles in the vulnerability lifecycle, and proposes a multi‑dimensional framework for risk mitigation and safe AI‑assisted development.
This article compiles ten practical code snippets and command patterns—from Go error handling and Git workflows to defensive programming tricks—that Tencent engineers rely on daily, helping developers build muscle memory for common tasks.
This guide explains the concept of human‑in‑the‑loop (HITL) interruptions in LangGraph, outlines the core mechanisms such as persistent state and dynamic/static interrupts, and provides detailed Python examples for four classic patterns—approval/rejection, state editing, tool‑call review, and input validation—plus advanced topics like parallel interrupts and MCP‑based tool integration.
This article explains how to give large language model agents lasting memory by combining short‑term and long‑term storage in LangGraph, covering concepts, implementation details, database persistence, tool integration, semantic search, memory‑management strategies, checkpoint handling, and a multi‑agent supervisor example.
This article provides a comprehensive, step‑by‑step explanation of the Transformer architecture that underpins large language models, covering tokenization, embeddings, positional encoding, attention mechanisms, feed‑forward networks, layer stacking, a detailed translation example, visualized attention weights, and a survey of recent open‑source LLM designs such as DeepSeek V3, OLMo 2, and Gemma 3.
This article examines whether large language models truly think, explores the origins of deep reasoning through transformer architectures and scaling laws, reviews chain‑of‑thought and its variants, and analyzes how reinforcement learning from human feedback—including PPO, DPO, and GRPO—helps internalise step‑by‑step reasoning while pointing to future directions such as atomic thought, hierarchical models, and training‑free in‑context knowledge bases.
This article systematically dissects Google’s open‑source gemini‑cli, revealing how it transforms a traditional command‑line terminal into an AI‑driven collaborative interface by detailing its ReAct loop, tool‑calling mechanisms, context management, and extensible architecture for building similar terminal agents.
This article details the year‑long exploration of Profile‑Guided Optimization (PGO) for WeChat’s backend, covering its theory, compiler implementations, practical experiments with Propeller and BOLT, transparent eBPF sampling, engineering challenges, and the measurable CPU and memory savings achieved across production services.
