A knowledge-sharing platform for Sohu's technology products. As a leading Chinese internet brand with media, video, search, and gaming services and over 700 million users, Sohu continuously drives tech innovation and practice. We’ll share practical insights and tech news here.
The article explains how Amper has been integrated into the Kotlin Toolchain as an Alpha feature, replacing its commands with a unified kotlin CLI, adding Maven publishing, C‑interop improvements, and IDE‑CLI consistency, and discusses the implications for Gradle’s role in Kotlin projects.
The article analyzes the emerging GEO (Generative Engine Optimization) attack that poisons RAG‑based AI search results, explains why single‑agent architectures are vulnerable, and details a multi‑agent orchestrator with whitelist tools, asynchronous cross‑validation, adversarial filtering, and UI provenance to robustly defend against such poisoning.
Android 17 introduces a system‑level MemoryLimiter that silently kills apps exceeding per‑device RAM limits, making bitmap memory the primary optimization target; the article explains the mechanism, detection methods, new Android Studio tools, and five concrete strategies to keep your app alive.
The article breaks down the Codex‑maxxing whitepaper into ten concrete workflow tricks—pinned threads, voice input, steering, file‑based memory, tool selection, mobile remote handling, automations, verifiable goals, side‑panel collaboration, and a closed‑loop process—showing how to turn Codex from a one‑off chatbot into a long‑running work system.
This article systematically reviews major LLM agent design patterns—including ReAct, CodeAct, static and dynamic planning, reflection, and human‑in‑the‑loop—detailing their core loops, code structures, trade‑offs, and practical use‑cases, and provides a decision tree to help developers choose the most suitable pattern for their tasks.
The article details how the team built a high‑performance, reliable cloud‑native gateway for millions of AI sandbox VNC sessions, addressing challenges of dynamic pod IPs, multi‑stage Web VNC traffic, session consistency, and security by using OpenResty, Lua scripts, Redis‑backed routing, cookie‑based state storage, and extensive Nginx tuning.
This article details the design and implementation of a high‑performance text content moderation system, covering the end‑to‑end workflow, the core Aho‑Corasick multi‑pattern matching algorithm, its double‑array Trie optimization, memory and speed benchmarks, and practical deployment considerations for large‑scale news client platforms.
This article explains how Kotlin's inline keyword eliminates lambda object allocation and virtual calls, enables non‑local returns and reified generics, discusses inline properties and their performance benefits, and outlines scenarios where inlining can backfire, helping developers use it wisely.
The article details a cloud‑native gateway design that solves the zero‑loss routing and session‑persistence challenges of massive AI sandbox Web VNC streams by dissecting protocol stages, exposing classic gateway pitfalls, and presenting a two‑phase URL‑plus‑cookie routing architecture built on OpenResty, Lua, and Redis.
The article outlines a six‑step workflow for leveraging Codex in research tasks—starting with reading the codebase, defining clear long‑term rules, planning complex changes, verifying assumptions, resetting the session after each task, and demanding explicit validation output—to make AI‑assisted development reliable and reproducible.
