Su San Talks Tech
Author

Su San Talks Tech

Su San, former staff at several leading tech companies, is a top creator on Juejin and a premium creator on CSDN, and runs the free coding practice site www.susan.net.cn.

922
Articles
0
Likes
1.7k
Views
0
Comments
Recent Articles

Latest from Su San Talks Tech

100 recent articles max
Su San Talks Tech
Su San Talks Tech
May 17, 2026 · Information Security

Nginx’s 18‑Year‑Old RCE Flaw Exposes One‑Third of Websites

A critical Nginx vulnerability (CVE‑2026‑42945, CVSS 9.2) discovered by depthfirst and F5 allows unauthenticated remote code execution via a single crafted HTTP request, affecting versions 0.6.27‑1.30.0 and roughly one‑third of global websites.

CVE-2026-42945Information SecurityRCE
0 likes · 11 min read
Nginx’s 18‑Year‑Old RCE Flaw Exposes One‑Third of Websites
Su San Talks Tech
Su San Talks Tech
May 15, 2026 · Artificial Intelligence

Step-by-Step Beginner’s Guide to Getting Started with Codex

This article walks readers through why many users are switching from Claude Code to Codex, explains the two Codex product forms, details installation, account setup, UI navigation, permission choices, and demonstrates practical tasks such as generating reports, PPTs, web searches, automation, and building a snake game via the CLI, while also offering tips to avoid common pitfalls.

AI assistantAppCLI
0 likes · 16 min read
Step-by-Step Beginner’s Guide to Getting Started with Codex
Su San Talks Tech
Su San Talks Tech
May 15, 2026 · Artificial Intelligence

Understanding Rerank in Retrieval‑Augmented Generation (RAG)

The article explains why a reranking step is essential in RAG pipelines, describes how it refines the initial vector‑search results, compares mainstream rerank techniques, discusses practical engineering choices such as candidate set size and model selection, and outlines how to evaluate and tune rerank performance.

Cross-EncoderLLMModel selection
0 likes · 15 min read
Understanding Rerank in Retrieval‑Augmented Generation (RAG)
Su San Talks Tech
Su San Talks Tech
May 13, 2026 · Artificial Intelligence

Cut Claude Code Token Costs by Up to 89% with the Open‑Source RTK CLI

RTK is a high‑performance CLI proxy that filters and compresses command output before it reaches Claude Code’s 200k‑token LLM context, reducing token consumption by 60‑90% and cutting costs up to 89%, with step‑by‑step installation and usage instructions provided.

CLIClaude CodeLLM
0 likes · 5 min read
Cut Claude Code Token Costs by Up to 89% with the Open‑Source RTK CLI
Su San Talks Tech
Su San Talks Tech
May 12, 2026 · Artificial Intelligence

Managing All Claude Code AI Sessions with the New Agent View

Claude Code’s new Agent View lets developers open a single terminal interface to launch, monitor, and control multiple AI coding sessions, offering commands for background tasks, a Peek preview panel, Attach deep‑dive mode, git worktree isolation, status icons, and a full shortcut reference, all without losing sessions when terminals close.

AI codingAgent ViewCLI
0 likes · 10 min read
Managing All Claude Code AI Sessions with the New Agent View
Su San Talks Tech
Su San Talks Tech
May 12, 2026 · Cloud Native

How Nacos 3.2 Evolves into an Enterprise AI Governance Platform

Nacos 3.2 expands beyond a micro‑service registry to become a unified AI asset governance platform, introducing AI Registry, MCP Registry, a three‑layer Skill security sandbox, Copilot assistance, and A2A protocol integration for seamless enterprise AI adoption.

A2A ProtocolAI RegistryMCP Registry
0 likes · 11 min read
How Nacos 3.2 Evolves into an Enterprise AI Governance Platform
Su San Talks Tech
Su San Talks Tech
May 11, 2026 · Artificial Intelligence

How Google’s Open‑Source MCP Toolbox Secures AI Agent Database Access

The article analyzes the dangers of giving LLMs unrestricted database privileges, explains Google’s MCP Toolbox design that enforces least‑privilege, structured queries and authentication, provides a step‑by‑step Go integration guide, shares production pitfalls, and compares suitable use cases versus raw function calling.

AI agentGoMCP Toolbox
0 likes · 18 min read
How Google’s Open‑Source MCP Toolbox Secures AI Agent Database Access
Su San Talks Tech
Su San Talks Tech
May 11, 2026 · Artificial Intelligence

Designing a Production‑Ready LLM Gateway: Architecture, Routing, Fallback, and Observability

This article outlines a production‑grade LLM Gateway design, detailing a three‑layer architecture, capability‑, cost‑, latency‑ and semantic‑based routing strategies, multi‑level fallback mechanisms, specialized load balancing, unified API adaptation, semantic caching, observability, and compares popular open‑source implementations.

FallbackLLMObservability
0 likes · 17 min read
Designing a Production‑Ready LLM Gateway: Architecture, Routing, Fallback, and Observability
Su San Talks Tech
Su San Talks Tech
May 9, 2026 · Databases

Why Can Redis Handle Over 100,000 QPS? A Deep Technical Breakdown

Redis can sustain over 100,000 queries per second thanks to four key pillars—memory‑first storage, highly optimized data structures like SDS and skip lists, a single‑threaded event loop with epoll multiplexing, and multi‑core I/O threading—each explained with benchmarks, code samples, and real‑world comparisons.

Data StructuresIO MultiplexingPerformance
0 likes · 10 min read
Why Can Redis Handle Over 100,000 QPS? A Deep Technical Breakdown