Official tech channel of 360, building the most professional technology aggregation platform for the brand.
The 360 AI Research Institute tackled the zero‑tolerance translation demands of airline maintenance by building a specialized parallel corpus and applying RAG‑enhanced, SFT‑fine‑tuned, and RL‑reinforced models, raising Chinese‑to‑English translation accuracy from 70% to 96% and enabling a one‑month rollout.
The MMKG‑RDS framework introduced by 360 AI Lab creates a complete pipeline—from multimodal document parsing and knowledge‑graph construction to customizable task synthesis and multi‑dimensional quality assessment—enabling the production of high‑quality reasoning data that significantly boosts large‑model performance across diverse domains.
This article explains Anthropic's Agent Skills, compares them with MCP, Projects, and other agent platforms, and provides a step‑by‑step guide to creating a practical Skill for uploading article images to an image‑hosting service.
This article details how a front‑end team generated high‑quality React code from only UI screenshots by iteratively applying imgcook, an Agent‑driven MCP service, and custom prompts, achieving up to 80% code usability and demonstrating a repeatable script‑based workflow.
This article presents fifteen practical chunking techniques—ranging from line‑by‑line and fixed‑size chunking to semantic and hierarchical methods—explaining their principles, ideal use‑cases, concrete input examples, chunk outputs, and key advantages or cautions for improving Retrieval‑Augmented Generation with large language models.
LangChain 1.0 replaces fragmented agent code with a production‑ready framework that unifies model outputs, simplifies tool integration, introduces content_blocks for consistent response handling, and adds a middleware system for privacy, summarization, and human‑in‑the‑loop safety, dramatically improving developer efficiency and reliability.
WebGPU and WebAssembly together break the performance ceiling of traditional JavaScript‑WebGL stacks, enabling native‑grade GPU compute, multithreaded workloads, and real‑time AI, video, and 3D rendering in browsers, while offering practical optimization techniques, code examples, and a roadmap of challenges and future trends.
This article explains the definitions, differences, and integration trends of Knowledge Bases and Knowledge Graphs within Retrieval‑Augmented Generation, helping developers decide which technology best fits their AI system requirements.
At the 2025 China Internet Conference, 360 joined the launch of the Intelligent Agent Innovation Promotion Plan, outlining a five‑level agent framework, showcasing high‑performance L3/L4 agents, and pledging to leverage its AI and security expertise to drive a collaborative intelligent‑agent ecosystem in China.
Zhou Hongyi’s article highlights AI’s pivotal role in the new technological wave, outlines the challenges of large models, introduces a five‑level taxonomy of intelligent agents, showcases 360’s swarm‑based deployments, and stresses the urgent need for security‑focused agents as AI reshapes enterprises.
