Official account of Tencent Technology. A platform for publishing and analyzing Tencent's technological innovations and cutting-edge developments.
This article explores how a multi‑agent AI system dramatically improves 0‑day vulnerability detection by automating code audit, reducing false positives, and outperforming traditional static analysis tools in large‑scale real‑world benchmarks.
Kuikly, Tencent’s Kotlin Multiplatform‑based cross‑platform framework, has been extended to support HarmonyOS with native performance, offering Compose DSL, high‑performance rendering, Kotlin Native adaptation, debugging tools, and detailed optimization strategies that achieve near‑native speed and dynamic UI capabilities across Android, iOS, Web, and mini‑programs.
This article provides a concise, easy-to-understand introduction to large language models, the transformer architecture, prompt engineering, temperature settings, function calling, the Model Context Protocol (MCP), agent communication (A2A), and future AI programming trends, using simple analogies and illustrative examples.
This article explains the Model Context Protocol (MCP) for AI development, detailing its definition, core components, communication methods, execution process, relationship with agents and function calling, ecosystem growth, and future implications and challenges.
The preview release of the 3‑billion‑parameter VLR1‑3B multimodal model demonstrates state‑of‑the‑art reasoning on math benchmarks, outperforms many commercial closed‑source models, and shows promising results on geometry, physics, and general vision tasks, while also revealing typical hallucination issues.
An in‑depth overview traces the development of AI agents from early LLM milestones to modern “class‑Agent” models, examines core components such as memory, tool use, planning and reflection, analyzes current limitations, and outlines emerging solutions like workflows, multi‑agent systems, and model‑as‑product paradigms.
The USENIX‑selected paper on Tencent’s TGW cloud gateway reveals how a modular, multi‑layer architecture achieves up to 2.9‑fold throughput gains, seconds‑level elastic scaling, loss‑less hot migration, and sub‑second fault recovery, offering a blueprint for resilient large‑scale cloud networking.
This article examines the evolution of large model technologies—including Retrieval‑Augmented Generation, AI agents, and multimodal models—detailing their technical foundations, practical challenges, industry applications, and future development trends, offering a comprehensive perspective for AI practitioners and researchers.
This article gathers engineers’ experiences and advice on selecting open‑source licenses, explaining GPL’s contagion risk, comparing permissive (MIT/Apache) and copyleft (GPL/LGPL) options, and offering practical guidelines for balancing technical freedom with commercial security across different project scenarios.
This article provides a detailed Chinese‑to‑English summary of Andrej Karpathy’s 7‑hour LLM tutorial, covering chat process analysis, tokenization, pre‑training data pipelines, model architecture, training strategies, post‑training fine‑tuning, reinforcement learning, chain‑of‑thought reasoning, and current industry applications.
