01
Artificial Intelligence 11 min read
Boost Qwen3.6 with MTP: 1.5× Faster Local Deployment for Claude Code
Old Zhang's AI Learning
104
trending score
Category All Categories
02
Bun v1.3.14 Released: Rust Rewrite Nears Completion, May End Zig Era
Node.js Tech Stack 15 min read Backend Development
5
0
03
Why Robots Need World Models: A Joint Survey from Leading Institutions
Machine Heart 14 min read Artificial Intelligence
2
0
04
Can Your PC Run Large Language Models? Meet BenchLoop, the Local Benchmarking Tool
Old Zhang's AI Learning 14 min read Artificial Intelligence
2
0
05
A 18‑Year‑Old Nginx RCE Flaw Finally Exposed (CVE‑2026‑42945)
Black & White Path 5 min read Information Security
2
0
06
Efficient AI Coding with Claude Code: Essential ECC Tools and Minimal Install
Frontend AI Walk 14 min read Artificial Intelligence
2
0
07
GPT Plus vs. Pro: 2026 Buying Guide for Developers
Java Architect Essentials 4 min read Artificial Intelligence
2
0
08
How a Multi‑Agent Team Built an HTML Page in One Take (No More “Continue” Prompts)
Machine Learning Algorithms & Natural Language Processing 14 min read Artificial Intelligence
2
0
09
Why Codex /goal Goes Beyond Simple Looping for Long‑Running Agents
Architect 20 min read Artificial Intelligence
2
0
10
7 Advanced CLAUDE.md Tricks to Double Claude Code’s Effectiveness
Spring Full-Stack Practical Cases 7 min read Artificial Intelligence
2
0
11
How China’s MUSA GPU Backend Earned Native Support in SGLang’s Mainline
Machine Heart 12 min read Artificial Intelligence
2
0
12
One‑Click Bug Fixes: AI‑Powered Log Diagnosis Skill with MCP
dbaplus Community 14 min read Backend Development
2
0
13
Why Can Redis Sustain Over 100k QPS? A Deep Technical Dive
IT Services Circle 9 min read Databases
1
0
14
Google I/O 2026 Unveils Gemini Omni and Gemini 3.5 Flash – A Leap in Multimodal AI
IT Services Circle 13 min read Artificial Intelligence
1
0
15
The Three Evolutions of AI Engineering: Prompt, Context, and Harness
Tencent Tech 19 min read Artificial Intelligence
1
0
16
Why Convert Docs to Markdown for LLMs? Meet the Open‑Source MarkItDown Tool
Su San Talks Tech 6 min read Artificial Intelligence
1
0
17
Qwen3.7-Max Sets New Agent Benchmarks – China’s New Model King
Machine Heart 13 min read Artificial Intelligence
1
0
18
How Ontology‑Driven Agents Enable Controllable Execution in Harness Engineering
DataFunTalk 20 min read Artificial Intelligence
1
0
19
Is Gemini 3.5 Flash Really That Powerful? Google Turns Its Search Box into an AI Agent
Machine Heart 9 min read Artificial Intelligence
1
0
20
AI‑Powered Research Workflow: When to Trust the Tools and When to Supervise
SuanNi 17 min read Artificial Intelligence
1
0
21
30 Essential SQL Query Optimization Techniques
Architect's Guide 10 min read Databases
1
0
22
18 Essential Shell Scripts for Everyday Linux Operations
Linux Tech Enthusiast 19 min read Operations
1
0
23
When $gt Becomes a Master Key: Bypassing MongoDB API Logins via NoSQL Injection
Black & White Path 12 min read Information Security
1
0
24
Two Open‑Source AI Tools to Auto‑Generate HTML Slides and Hand‑Drawn Technical Diagrams
Geek Labs 9 min read Frontend Development
1
0
25
Can 99% Sparse Transformers Run Faster? Insights from the ‘Attention Is All You Need’ Authors
Machine Learning Algorithms & Natural Language Processing 8 min read Artificial Intelligence
1
0
26
Composer 2.5 Narrows the Gap to Claude Opus 4.7 with Ten‑Fold Cost Savings
Machine Learning Algorithms & Natural Language Processing 13 min read Artificial Intelligence
1
0
27
Mastering ramfs and tmpfs: Deep Dive into Linux’s High‑Speed In‑Memory Filesystems
Deepin Linux 32 min read Fundamentals
1
0
28
Why Chunk‑Based RAG Fails and How IdeaBlocks Improve Retrieval
AI Engineer Programming 10 min read Artificial Intelligence
1
0
29
Becoming a Hermes Agent Operator: Build, Configure, and Scale AI Marketing Agents on One VPS
AI Architecture Hub 23 min read Artificial Intelligence
1
0
30
Why Did the Nvidia H100 GPU Vanish in 2026?
Architects' Tech Alliance 10 min read Industry Insights
1
0
31
Why Storing Tokens in Redis Is the Right Answer in Interviews
Java Architect Essentials 6 min read Backend Development
1
0
32
Programming: Memorize or Create? Why Understanding Beats Rote Learning
Liangxu Linux 6 min read Fundamentals
1
0
33
Andrej Karpathy Joins Anthropic: Implications for the Next AI Talent War
Machine Heart 5 min read Industry Insights
1
0
34
When Does a Song’s Climax Start? GaMMA Lets Multimodal Models Grasp Music Timelines
Machine Heart 22 min read Artificial Intelligence
1
0
35
Add a Progress Bar to Linux cp and mv Commands
Linux Tech Enthusiast 3 min read Fundamentals
1
0
36
Building an AI‑Ready, Multi‑Modal Database Foundation for the Digital Intelligence Era
DataFunSummit 16 min read Databases
1
0
37
Why Long-Term Memory Needs Vision: How MemEye Evaluates Multimodal Agent Recall
PaperAgent 4 min read Artificial Intelligence
1
0
38
HyperEyes: Parallel Multimodal Search Agents Move from Deep to Wide for Efficiency
Machine Heart 9 min read Artificial Intelligence
1
0
39
Where Did the NVIDIA H100 Go? Memory and Packaging Bottlenecks Explained
Machine Heart 15 min read Industry Insights
1
0
40
Peter Steinberger’s $1.3 M Monthly Token Bill: OpenAI’s Subsidy Powers a 100‑Agent OpenClaw
IT Services Circle 7 min read Artificial Intelligence
1
0
41
Can a Single String Constant Crash the Go Compiler with OOM?
IT Services Circle 10 min read Fundamentals
1
0
42
Which Linux Distribution Is Best for Everyday Use Without Programming?
IT Services Circle 5 min read Fundamentals
1
0
43
10 Common MySQL Index Failure Scenarios – Which Ones Affect You?
Ops Community 32 min read Databases
1
0
44
Why Microsoft Is Dropping the Superior Claude Code for Its Own Copilot CLI
Java Tech Enthusiast 8 min read Artificial Intelligence
1
0
45
Anthropic Code w/ Claude Conference: How AI Cut a 10‑Week Project to 4 Days
Data Party THU 35 min read Artificial Intelligence
1
0
46
Why Logs Alone Fail in Spring Boot: Achieving True Observability
Spring Full-Stack Practical Cases 9 min read Backend Development
1
0
47
How Knora’s Ontology‑Enhanced AI Tackles Hallucinations and Execution Gaps in Enterprise Deployments
DataFunTalk 16 min read Artificial Intelligence
1
0
48
How New LLM Architectures Like Gemma 4 and DeepSeek V4 Cut Long‑Context Costs
Machine Heart 25 min read Artificial Intelligence
1
0
49
How Instant Retail Is Quietly Breaking Away From Traditional E‑Commerce Logic
Digital Planet 12 min read Industry Insights
1
0
50
Why One‑Shot AI Prompts Fail and How 19 Iron Rules Build a Factory‑Style Workflow
ZhiKe AI 14 min read R&D Management
1
0