Official account of Tencent Technology. A platform for publishing and analyzing Tencent's technological innovations and cutting-edge developments.
AngelSlim introduces a system‑wide speculative decoding framework called Eagle3 that combines lightweight draft models with parallel verification by large models, delivering up to 1.9× faster inference across LLM, vision‑language, and speech tasks while remaining open‑source and deployment‑ready.
This article analyzes the shortcomings of spec‑driven tools like speckit and openspec in complex enterprise environments, introduces context engineering and compound engineering concepts, and presents a practical AI‑engineered workflow that reduces marginal cost, captures knowledge automatically, and makes AI tools feel invisible to developers.
This article explains the ReAct framework, which augments large language models with explicit reasoning, tool use, and observation loops to overcome hallucinations, improve transparency, and enable dynamic interaction with external environments across diverse tasks.
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.
