#token bucket algorithm
34 related articles
·3 min
Post-Mortem and Lessons from OpenAI's Accidental DDoS Attack on Hugging Face
A post-mortem of OpenAI's accidental DDoS on Hugging Face, analyzing the technical causes of unexpected traffic floods, AI infrastructure fragility, and defense strategies for large-scale API consumers.
Read more →
·3 min
Cursor Browser Worker Parallelization: Practical Strategies for Working Within Rate Limits
Learn how to parallelize Cursor browser Workers from serial to parallel execution using distributed Worker pools, proxy pools, token bucket algorithms, and exponential backoff to compress 2000-3000 page scraping tasks from hours to 15-20 minutes.
Read more →
·3 min
System Design Primer: An In-Depth Analysis of the 360K-Star System Design Study Guide on GitHub
In-depth analysis of the 360K-Star System Design Primer on GitHub, covering distributed system design fundamentals, interview case studies, and Anki flashcards to help you master large-scale architecture design.
Read more →
·2 min
LangSmith Gateway Explained: Core Capabilities and Architecture of LangChain's Enterprise AI Model Gateway
Deep dive into LangSmith Gateway's core features including cost control, rate limiting, PII redaction, coding agent integration, and open-source model access for enterprise AI infrastructure.
Read more →
·3 min
Why Can't Word2vec Handle Out-of-Vocabulary Words? OOV Problem Explained with Solutions
Deep dive into why Word2vec can't handle OOV words, explaining the lookup table mechanism and covering solutions like FastText subwords, UNK tokens, and BERT.
Read more →
·4 min
MCP-Billing: A One-Stop Solution for MCP Server Authentication, Billing, and Monetization
MCP-Billing is a self-hosted Next.js boilerplate providing OAuth 2.1 auth, Stripe usage billing, API key management, and Redis rate limiting for MCP servers—one-time €79 payment with no revenue share.
Read more →
·4 min
Infrastructure Architecture for Agent Applications: Four Core Patterns Explained
A deep dive into infrastructure architecture patterns for production-grade Agent applications, covering state persistence, sandbox isolation, LLM observability, and cost control.
Read more →
·4 min
Infrastructure Architecture for Agent Applications: Four Core Patterns Explained
Deep dive into infrastructure architecture patterns for production-grade Agent applications, covering state persistence, sandbox isolation, LLM observability, and cost control.
Read more →
·3 min
Ollama API Key Proxy: Multi-Key Rotation to Solve Rate Limiting Issues
Learn how Ollama API Key Proxy solves cloud LLM rate limiting through reverse proxy with round-robin key rotation, 429 auto-cooldown, and smart retry logic.
Read more →
·3 min
Zero-Cost QQ Group Minesweeper Bot in 6 Minutes with DeepSeek
Step-by-step guide to using DeepSeek with the OICQ framework to generate a runnable QQ group Minesweeper bot Python script in 6 minutes — zero cost, real pitfalls included.
Read more →
·2 min
Cursor Pro Keeps Throwing Errors? A Deep Dive into AI Coding Tool Stability Issues
Cursor Pro users hitting persistent errors? This deep dive covers the top causes — rate limits, proxy issues, account status — plus a 6-step troubleshooting guide.
Read more →
·3 min
Agent Tool Call Failures? Layered Fault Governance Is the Right Answer
How to handle Agent tool call failures? Learn a 3-tier fault governance system: exponential backoff, self-correction loops, and human-in-the-loop for high-risk failures.
Read more →
·4 min
Retrieval vs. Reasoning: Does Search Technology Still Matter in the Age of LLMs? Six Experts Debate
When ChatGPT can answer directly, does retrieval still matter? Six experts from Microsoft, IIT Delhi debate parametric memory limits, BM25's endurance, and where retrieval ends and reasoning begins.
Read more →
·3 min
Getting Started with Codex: A Comprehensive Comparison with Claude Code and How to Choose
A deep comparison of Codex vs. Claude Code on pricing, stability, and frontend/backend strengths — plus how to choose between Cursor, Claude Code, and Codex.
Read more →
·5 min
AI Tool Runs Amok: 171 Charges Totaling Nearly $1,800 — How to Avoid the Auto-Billing Trap
A user's American Express card was auto-charged 171 times by an AI service, totaling nearly $1,800 with no warning. This article analyzes pay-as-you-go risks and offers practical protection: spending limits, virtual cards, and automation monitoring.
Read more →
·5 min
Java Backend Interview Sprint: A Systematic Methodology From Rote Q&A to Scenario Questions
How can you prepare efficiently for a Java backend interview? This article breaks down the core methodology of "process-driven interview engineering," covering resume optimization, understanding principles, scenario analysis frameworks, and production troubleshooting.
Read more →
·5 min
AI Data Centers Competing for Power: Why U.S. Manufacturing Energy Costs Keep Soaring
The explosive expansion of AI data centers is voraciously consuming electricity, directly driving up U.S. manufacturing energy costs. This article dissects the crowding-out effect and the path forward.
Read more →
·7 min
GPT-5.6 Full Model Lineup Hands-On Guide: A Deep Dive into API Relay Stations and Their Risks
The full GPT-5.6 model lineup is live. How can domestic developers access it at low cost via API relay stations? This article explains the principles, registration, token setup, client integration, and key risks.
Read more →
·7 min
Dify Enterprise System Integration in Practice: Building a Project Management AI Copilot with Workflows
Using a project management system as an example, this article details how to use the Dify low-code platform to achieve AI-powered integration of enterprise internal systems through interface capture and workflow orchestration.
Read more →
·2 min
ChatGPT Codex Now Rolls Over Unused Resets: AI Coding Finally Free from Quota Interruptions
OpenAI introduces reset rollover for ChatGPT Codex — unused quota no longer expires. Learn how this update eliminates quota anxiety and reshapes AI coding competition.
Read more →