#DRaFT
674 related articles
Tutorials·3 min
Claude Code for Academic Research: 3 Skills to Build a Paper Workflow
How to build a structured paper workflow with Claude Code: three core Skills for material classification, literature evidence matching, and reviewer simulation, plus six reusable AI-assisted research principles.
Read more →
Tutorials·3 min
llama.cpp MTP Acceleration Deployment Guide: Configuration Steps & Real-World Benchmarks
Guide to enabling MTP multi-Token prediction acceleration in llama.cpp, covering CUDA setup, desktop configuration, model selection, and benchmarks showing ~60 Token/s with Qwen3 27B.
Read more →
Tech Frontiers·2 min
Anthropic Confidentially Files S-1, AI Giant's IPO Process Officially Begins
Anthropic has confidentially filed an S-1 with the SEC, officially launching its IPO process. Analysis of the filing's implications, its $60B valuation, and the impact on the AI industry.
Read more →
Product Reviews·3 min
GPT-5.1 Deep Dive: 10 Core Features That Transform AI from Chat Tool to Work Partner
Deep dive into GPT-5.1's 10 core feature upgrades including dual-mode switching, project agents, coding assistance, tool orchestration, and 24-hour prompt caching to boost your productivity.
Read more →
Tutorials·4 min
Semi-AI Mode: A Pragmatic Approach to API Automation Testing Frameworks
Explore the semi-AI approach to API automation testing: why pure AI fails, framework design principles, technology choices, and clear human-AI division of labor for practical implementation.
Read more →
Tutorials·3 min
Stable Diffusion Local Deployment Guide: Run AI Image Generation Free with 8GB RAM
Complete guide to deploying Stable Diffusion locally. Covers hardware requirements, one-click installation, and model setup. Run AI image generation free with 8GB RAM.
Read more →
Product Reviews·4 min
OpenHuman Deep Dive: A Context-First Open-Source Personal AI Agent
Deep dive into OpenHuman open-source AI Agent: context-first architecture, Rust+React hybrid, Memory Tree system, Token Juice compression, and multi-model routing.
Read more →
Tutorials·3 min
oMLX + MTP + Qwen3.6: Local AI Coding Speed Breaks New Records
Using oMLX with MTP and Qwen3.6 35B on Apple Silicon Mac to achieve 86.7 tokens/s local coding speed, building a full-stack app in under 5 minutes.
Read more →
Deep Dives·4 min
Can AI Agents Replace a Development Team? A Practical Guide for Non-Technical People
Can non-technical people use AI Agents to build virtual dev teams? From CEO Agent to Developer Agent, we analyze the theory vs. reality and offer a practical implementation guide.
Read more →
Tutorials·2 min
Six Pitfalls and a Three-Layer Solution for Implementing AI-Powered API Test Automation
Deep dive into six common pitfalls of AI-generated API automation scripts and a three-layer solution covering diagnosis and optimization for real-world implementation.
Read more →
Tutorials·3 min
No Code Written: Launching a Personal Website in Two Hours with Gemini + Qoder
Build a website with zero coding! Learn how to use Gemini 3 for frontend code generation and Qoder for debugging and deployment to launch a personal site in two hours.
Read more →
Tutorials·3 min
The Right Way for Beginners to Build Products with AI: The Iterative Build Loop Explained
Vibe Coding isn't just chatting with AI. Learn the Iterative Build Loop: Discuss, Document, Develop, Learn — with VS Code and Claude Code to build products from scratch.
Read more →
Product Reviews·2 min
Claude Code Fast Mode Price Cut: Dual-Mode Workflow Reshapes the AI Programming Experience
Anthropic cuts Claude Opus 4.8 Fast mode pricing. Learn how the dual-mode workflow—Fast for interactive coding, Normal for async tasks—reshapes AI programming.
Read more →
Tech Frontiers·2 min
General-Purpose AI Model Cracks Major Open Problem in Mathematics: A Milestone Moment Has Arrived
OpenAI CEO Sam Altman announces a general-purpose AI model has solved a major open math problem. We analyze this milestone, the leap from specialized to general AI, and its implications for science.
Read more →
Tech Frontiers·1 min
Windsurf Integrates Claude Opus 4.7 Fast Mode with 2.5x Speed Boost
Windsurf integrates Claude Opus 4.7 fast mode with 2.5x speed boost while retaining full intelligence. Analysis of its impact on developer productivity and AI coding tool competition.
Read more →
Tech Frontiers·2 min
SGLang v0.5.12.post1 Released: DeepSeek V4 Stability Fixes and Blackwell Adaptation
SGLang v0.5.12.post1 stability patch details: 12 critical fixes covering DeepSeek V4 garbled text and crashes, NIXL PD disaggregated inference logic, Blackwell B300 adaptation, and cold start optimization.
Read more →
Industry Insights·2 min
AMD MI355X Beats B200: Full-Stack Optimization Breakdown for 5% Lower TCO on DeepSeek-R1 Inference
AMD Instinct MI355X achieves 5% lower TCO than NVIDIA B200 on DeepSeek-R1 disaggregated inference via SGLang+MoRI full-stack optimization with 1.25x per-GPU throughput.
Read more →
Tutorials·2 min
Coze Workflow for Auto-Generating Emotional Short Videos: A Zero-Code Tutorial
A detailed breakdown of automating emotional short video production with Coze workflows — from script generation and TTS to CapCut draft packaging, all zero-code.
Read more →
Tutorials·1 min
Build AI Agents from Scratch: A Practical Guide to the Coze Platform
Learn how to build AI agents with zero coding on ByteDance's Coze platform. Covers 10 hands-on projects including DeepSeek-WeChat integration, auto-emails, and poster/PPT creation.
Read more →
Tutorials·3 min
DeepSeek V4 Flash MTP Speculative Decoding Real-World Test: A Guide to 20% Faster Local Inference
Real-world testing of DeepSeek V4 Flash with MTP speculative decoding: ~20% speedup for code generation, minimal gains for text. Covers memory overhead, accuracy differences, Q4 vs Q3 quantization, and full deployment tutorial.
Read more →