Official account of Tencent Technology. A platform for publishing and analyzing Tencent's technological innovations and cutting-edge developments.
The article explains how Tencent’s Wuji low‑code platform uses a de‑templated, data‑first approach, automatic UI inference, progressive development layers, and AI assistance to let developers quickly build and customize a wide range of internal systems while maintaining integration and openness.
Augment, a newly funded AI programming assistant that tops the SWE‑bench benchmark with a 65.4% score and a 200 k‑token context window, promises massive productivity gains for developers but also introduces sophisticated security threats such as malicious memory prompts, back‑door context injection, compromised guidelines, and risky multi‑task collaboration protocols, prompting calls for layered defenses and vigilant monitoring.
Kuikly, Tencent’s Kotlin‑Multiplatform‑based cross‑platform framework, combines native‑level performance with dynamic page updates across Android, iOS, HarmonyOS, Web and mini‑programs, leveraging a two‑tree rendering architecture, DSL‑driven UI, and lightweight native components to boost development efficiency.
Fred’s practical guide expands Anthropic’s “Build effective agents” by offering a technical selection framework, clear definitions of agents versus workflows, a suite of reusable design patterns such as prompt‑chain routing and orchestrator‑worker loops, real‑world case studies, and concrete implementation tips that emphasize simplicity, transparency, and effective tool‑prompt engineering.
Conan‑Embedding‑V2, a newly trained 1.4 B‑parameter LLM with a custom tokenizer, 32 k token context, SoftMask, cross‑lingual retrieval data and dynamic hard‑negative mining, delivers state‑of‑the‑art multilingual embeddings that surpass larger models on both English and Chinese MTEB benchmarks while remaining compact and fast.
Linux treats all I/O devices as files, enabling a single thread to monitor many descriptors via I/O multiplexing; while select and poll use linear scans and suffer size limits, epoll employs an event‑driven red‑black tree with edge‑triggered mode, offering scalable, high‑performance handling for thousands of concurrent connections.
This practical guide walks through the full Transformer architecture for Chinese‑to‑English translation, detailing encoder‑decoder structure, tokenization and embeddings, batch handling with padding and masks, positional encodings, parallel teacher‑forcing, self‑ and multi‑head attention, and the complete forward and back‑propagation training steps.
The article examines the Model Context Protocol (MCP), detailing its microkernel‑based technical architecture, development timeline from Anthropic’s 2024 release to industry adoption, hands‑on implementation examples, and business use cases such as multi‑agent QQ robots, highlighting MCP’s potential to standardize AI tool integration across industries.
The article examines critical security flaws in Anthropic’s Model Context Protocol (MCP) and Google’s Agent‑to‑Agent (A2A) protocol—such as hidden tool‑poisoning, rug‑pull, and command‑injection attacks that can hijack AI agents and leak data—while proposing hardening measures like authentication, sandboxing, digital signatures, fine‑grained permissions, and robust OAuth‑based consent to safeguard AI‑agent communications.
The Woodpecker team shows that AI‑generated code, exemplified by Simon Willison’s HTML slideshow tool, can embed unsanitized inputs that create exploitable XSS flaws, and they recommend zero‑trust AI prompts, rigorous input filtering, CSP, AI‑assisted scanning, and secure supply‑chain practices to mitigate such risks.
