985 related articles
Tech FrontiersCloudflare contributes decode KV cache offload and Mooncake recovery fixes to SGLang, resolving garbled output under high concurrency for Kimi K2.6 and enabling automatic fault recovery in distributed inference.
Tech FrontiersSGLang team hosts an Agent Loops Office Hour exploring inference optimization for agentic loops, covering KV Cache reuse, low-latency multi-turn dialogue, and tool calling techniques.
Llama 3.3 70B In-Depth Review: Testing…
Meta releases Llama 3.3 70B open-source model with just 70B parameters rivaling 405B performance. Tested on 13 logic, math, and coding questions, it passed 12 — reshaping the open-source model landscape.
API Aggregation Proxy Platforms Tested…
Hands-on testing of an API aggregation proxy platform's model calling capabilities, including GPT-Image2 image generation, cost analysis, and coverage of 100+ models like Claude and Gemini.
Six Foundational Upgrades to Claude Co…
Anthropic's largest-ever foundational upgrade to Claude Code fixes six critical issues at once—terminal flickering, thinking freezes, cryptic errors, context deadlocks, unstable connections, and session crashes—shifting AI coding competition to the infrastructure layer.
BMad-Method: Building an AI Agile Deve…
Deep dive into BMad-Method, an open-source multi-agent framework simulating a full agile team—from business analysis to QA—supporting Claude Code, Cursor, and more.
Claude Code Source Code Study Guide: E…
Learn AI Agent development from Claude Code's 510K lines of source code, covering Agent Loop, context compression, multi-Agent orchestration, and two efficient study methods.
Claude Code Monitor Tool Explained: Ev…
Deep dive into Claude Code's new built-in Monitor tool. Learn how event-driven monitoring replaces polling via Stream Filter and Poll and Diff modes, dramatically reducing token consumption.
Major Claude Code Update: A Complete G…
Deep dive into Claude Code's new Agent View and Goal system, covering multi-agent parallel management, background sessions, and result-oriented autonomous execution.
ABCoder in Practice: A Demonstration o…
A practical comparison using Hertz framework SSE services shows how ABCoder uses MCP protocol to let AI models consult real source code, solving LLM code hallucination problems.
Tech FrontiersOpenAI launches Rosalind Biodefense, offering GPT-Rosalind to government agencies to accelerate pathogen surveillance, vaccine R&D, and pandemic preparedness using AI.
ResearchDeep dive into AISTATS 2024 paper MixupMP: revealing Deep Ensembles' fundamental UQ flaws and fixing them via Mixup augmentation and Martingale Posterior framework for better calibration and OOD detection.
Deep Dive into Cursor's Pay-Per-Use Re…
Deep analysis of Cursor's pay-per-use refill plugin: account rotation mechanism, tiered discounts, full model support, and objective assessment of compliance risks and data security concerns.
AI Programming Spec Sheets: 30 Lines o…
Replace vague prompts with spec sheets—30 lines of config gets AI coding right the first time. Covers the six-element framework, three-tier boundaries, and three iron rules to eliminate rework.
Claude Opus 4.8 Hands-On: What Can You…
Hands-on testing of Claude Opus 4.8's coding and creative abilities, including Mario game and Slay the Spire-style card game development, quota consumption, and real-world bug frequency.
Claude Code Desktop Installation & Con…
Step-by-step guide to install Claude Code Desktop, use it without an account via Developer Mode, integrate DeepSeek models through CSwitch, add Chinese localization, and configure custom Skills.
Getting Started with Claude Code: 5 Co…
Deep dive into the core differences between Claude Code and regular AI chat tools across 5 dimensions: interaction, context understanding, execution, memory, and tool invocation.
AI + Jupyter Notebook: A Practical Met…
The hardest part of STEM is the gap between theory and practice. Learn how to use Jupyter Notebook with AI Coding Agents to auto-generate interactive tutorials for math, physics, statistics, and more.
Deep Dive into Three Major LLM Career …
Deep analysis of three core LLM roles—Application Engineer, Development Engineer, and Algorithm Engineer—covering technical requirements, salary thresholds, and career prospects including RAG, fine-tuning, and inference deployment.
Cursor + MCP in Practice: A Complete G…
A detailed guide on integrating Playwright MCP Server with Cursor, covering Node.js setup with NVM, NPM mirror configuration, and building a browser automation agent step by step.