Avatar 🍥

KnightLi Blog

记录并分享日常

  1. Home
  2. About
  3. Archives
  4. Search
  5. Links
    1. Dark Mode

Archives

2026 507
2025 23
2024 5
2023 9
2022 33
2021 5
2020 8

Categories

AI Tools Technical Docs Hardware Development Tools AI Industry Operations Security Updates Business Analysis

Tags

AI Agent AI Tools AI Coding Codex Developer Tools Claude Code Local LLM Openai MCP Linux Claude Python Anthropic Ubuntu ChatGPT Open Source Ollama Llama.cpp NAS Gemini Prompts AI Art Game Development Godot LLM AI Models GPU Windows Cybersecurity DeepSeek
AI Tools

Prompt-Vault: a prompt specification library for testing AI coding ability

A summary of w512/Prompt-Vault: Bubble Sort visualization, todo list, sorting visualization, Kanban board, and Tauri Markdown editor prompts organized by difficulty for testing AI coding agents.

2026-05-15
4 minute read
中文简体 中文繁體 日本語 Español
AI Tools

What is Token Efficiency? DeepSeek V4, big-model planning, and small-model execution

A practical view of Token Efficiency in AI coding: DeepSeek V4 Pro / Flash positioning, big models for planning and consultation, small models for execution, plus context budgets, DAG orchestration, task replicas, evaluation, and atomic business workflows.

2026-05-15
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Superpowers: a skills framework that pulls coding agents back into engineering process

A summary of obra/superpowers: positioning, installation targets, base workflow, skills library, and boundaries. It combines brainstorming, planning, TDD, code review, worktrees, and subagents into a coding-agent methodology.

2026-05-15
4 minute read
中文简体 中文繁體 日本語 Español
Hardware

Honeywell PTM7950 confusion: do not judge only by thickness, origin, or black spots

A practical look at PTM7950 and PTM7950SP market confusion: 0.2 mm vs 0.25 mm, origin, black spots, color, COA, and authorization cannot alone prove authenticity or quality. Buyers should focus on batch traceability, testing, quality control, and after-sales support.

2026-05-15
5 minute read
中文简体 中文繁體 日本語 Español
AI Tools

mattpocock/skills Explained: How Matt Pocock Uses Skills to Constrain AI Coding

An analysis of Matt Pocock’s mattpocock/skills repository: how grill-me, grill-with-docs, TDD, diagnose, and architecture review bring Claude Code, Codex, and other AI coding tools back to clarification, testing feedback, and maintainability.

2026-05-15
4 minute read
中文简体 中文繁體 日本語 Español
Technical Docs

GPT-5.5 Prompt Migration Guide: Why old prompts should be trimmed before rewritten

A practical summary of OpenAI's GPT-5.5 prompting guide: shorter outcome-first prompts, reasoning effort, preambles and phase, retrieval budgets, validation rules, and what to remove first when migrating old prompts.

2026-05-15
15 minute read
中文简体 中文繁體 日本語 Español
AI Tools

What is cc-haha? A project that turns Claude Code into a desktop workbench

A look at NanmiCoder/cc-haha: its positioning, desktop workbench, Computer Use, multi-model setup, H5 remote access, installation flow, and risk boundaries.

2026-05-14
9 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Codex /goal vs Claude Code /goal: running long tasks until they are done

A comparison of the /goal command in Codex CLI and Claude Code: both target long-running tasks and completion conditions, but they differ in availability, setup, evaluation, and best-fit workflows.

2026-05-14
7 minute read
中文简体 中文繁體 日本語 Español
AI Industry

What Jensen Huang Was Really Saying in His CMU Speech

A concise reading of Jensen Huang's CMU speech: young people may need to relearn hardship, traditional career paths are changing, and the hard problems of the AI era will be harder than they first appear.

2026-05-14
4 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Connecting Claude to Fusion 360: An Example of Editing STEP Models With AI

A practical walkthrough of connecting Claude to Fusion 360: enabling the API/MCP service, connecting the port, letting AI analyze a gear structure, and converting a screw-mounted planetary gear into a bearing-based design.

2026-05-14
5 minute read
中文简体 中文繁體 日本語 Español
AI Tools

How Can Codex Use Chinese LLMs? Managing OpenAI-Compatible APIs with CCX

CCX is an AI API proxy and protocol-conversion gateway for Claude Messages, OpenAI Chat, OpenAI Images, Codex Responses, and Gemini. This article explains its positioning, deployment, endpoints, channel orchestration, environment variables, and operational cautions.

2026-05-13
8 minute read
中文简体 中文繁體 日本語 Español
AI Tools

How Can Codex Use Chinese LLMs? OpenAI-Compatible APIs and the CodexBridge Approach

CodexBridge wraps Codex CLI/SDK as an OpenAI-compatible chat API, allowing OpenWebUI, Cherry Studio, curl, and other clients to call local Codex through /v1/chat/completions. This article explains its use cases, deployment, sessions, multimodal input, structured output, and common configuration.

2026-05-13
6 minute read
中文简体 中文繁體 日本語 Español
Technical Docs

Computer Terms in Plain Language: What TTS, STT, API, RAG, and Agent Really Mean

Many computer terms sound impressive, but they often describe very simple things. This article explains common terms such as TTS, STT, API, SDK, CRUD, Cache, Queue, Embedding, RAG, and Agent in plain language.

2026-05-12
9 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Sulphur 2 LTX 2.3 Guide: 8GB VRAM, Local Video Generation, and Tool Choices

A practical Sulphur 2 LTX 2.3 video generation guide covering 8GB VRAM feasibility, text-to-video, image-to-video, local tool choices, GGUF-related assets, and common failure causes.

2026-05-12
9 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Running DeepSeek 4 Locally: Antirez's ds4 Experiment on Apple Silicon Mac

ds4 is a local DeepSeek V4 Flash inference engine written by Antirez for Apple Silicon, with CLI, HTTP server, and basic agent capabilities.

2026-05-11
3 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Why DeepSeek Became the Cost-Saving Key in This Round of AI Coding Tools

A look at the cost logic behind AI coding tools: why Claude Code, OpenClaw, Superpowers, and similar agent tools consume so many tokens, and why DeepSeek V4's long context and low cache pricing make it a key cost saver.

2026-05-11
7 minute read
中文简体 中文繁體 日本語 Español
AI Industry

ProgramBench Raw Leaderboard Data: Model Scores, Costs, and 200 Task Records

A structured copy of ProgramBench's public leaderboard, extended results, and 200 task records, preserving model scores, costs, call counts, test counts, and best scores.

2026-05-10
18 minute read
中文简体 中文繁體 日本語 Español
AI Industry

ProgramBench 0% Explained: The Scary Part Is Not Failure, but a Clear Roadmap

A concise explanation of ProgramBench, its 0% result, and what it really means for AI Coding: today's models cannot yet rebuild complete software from scratch, but full software engineering has now become a benchmarkable target.

2026-05-10
10 minute read
中文简体 中文繁體 日本語 Español
AI Tools

GPT-5.5 vs GPT-5.4 vs GPT-5.3-Codex: Which Model Should You Use?

Compare GPT-5.5, GPT-5.4, and GPT-5.3-Codex by use case, credit consumption, Codex workflows, coding, automation, translation, Q&A, and practical model selection.

2026-05-10
9 minute read
中文简体 中文繁體 日本語 Español
AI Tools

How to Choose AI Coding Plans: Convenience for Light Users, Flexibility for Heavy Users

A practical guide to choosing AI coding tools and model plans: light users should prioritize convenience, mid-level users should focus on value, and heavy users should decouple models from tools to avoid being locked into a single ecosystem.

2026-05-10
7 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Chrome Silently Downloads 4GB Gemini Nano: How to Check, Disable, and Delete It

A concise look at the controversy around Chrome silently downloading the roughly 4GB Gemini Nano local AI model, including file locations, affected platforms, Google's response, and how users can check and disable it.

2026-05-09
5 minute read
中文简体 中文繁體 日本語 Español
AI Tools

llama.cpp Multi-GPU Performance Guide: Offload, Split Mode, and VRAM Tradeoffs

A practical llama.cpp multi-GPU performance guide explaining offload behavior, split modes, tensor-split, VRAM limits, and when two 16GB GPUs beat or lose to one larger GPU.

2026-05-09
8 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Claude Code Limits Doubled: Anthropic Uses SpaceX Compute Expansion to Ease Usage Constraints

A summary of Anthropic's May 2026 increase to Claude Code and Claude API limits, and what its SpaceX compute partnership means for Claude Pro, Max, Team, and enterprise users.

2026-05-09
5 minute read
中文简体 中文繁體 日本語 Español
AI Tools

OpenAI's New Realtime Voice Models: GPT-Realtime-2, Live Translation, and Streaming Transcription

A concise look at OpenAI's May 2026 Realtime API voice models, including GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper: capabilities, use cases, pricing, and developer impact.

2026-05-09
5 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Claude Account Suspended? Claude Code Limits, Causes, and Appeal Guide

Understand common Claude account suspension causes, Claude Code limits, subscription issues, compliant troubleshooting steps, appeal options, and safer team-use practices.

2026-05-09
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

From PPT to Prototypes: Use Cases for Guizang PPT Skill and Huashu Design

A look at the positioning, capability differences, use cases, and practical recommendations for two open-source Agent design Skills: guizang-ppt-skill and huashu-design.

2026-05-09
6 minute read
中文简体 中文繁體 日本語 Español
Technical Docs

Dirty Frag CVE-2026-43284: Linux Local Privilege Escalation Risk and Mitigation Guide

A practical guide to Dirty Frag CVE-2026-43284, including affected Linux attack paths, CVE-2026-43500 / rxrpc risk, interim mitigations, patch priority, and post-compromise checks.

2026-05-09
6 minute read
中文简体 中文繁體 日本語 Español
Technical Docs

Btrfs Scrub Guide: Data Verification, Auto-Repair, and Regular Maintenance

A practical guide to what Btrfs scrub does, how to run it, when auto-repair works, NOCOW file risks, read-only scrub caveats, maintenance intervals, and bandwidth limiting.

2026-05-09
6 minute read
中文简体 中文繁體 日本語 Español
Hardware

Intel DG1, Arc A310, and Arc A380 Buying Guide: Low-Power GPUs and AV1 Display Cards Compared

A practical comparison of Intel Iris Xe DG1, Arc A310, and Arc A380 across architecture, VRAM, power, AV1 encode/decode, compatibility, and use cases such as NAS, HTPC, display output, light gaming, and hardware tinkering.

2026-05-09
6 minute read
中文简体 中文繁體 日本語 Español
AI Industry

Anthropic Partners With SpaceX: Frontier AI Enters the Heavy-Industry Compute Era

A look at the industry logic behind Anthropic's SpaceX compute deal: Claude usage limits, Colossus 1, GPU utilization, energy constraints, semiconductor supply chains, and AI infrastructure competition.

2026-05-08
6 minute read
中文简体 中文繁體 日本語 Español
AI Industry

Musk vs. OpenAI Trial: Nonprofit Mission, Control, and the AI Race

A structured overview of the lawsuit between Elon Musk, OpenAI, and Sam Altman: nonprofit mission, for-profit structure, control disputes, and what the trial may signal for AI governance.

2026-05-08
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

How to Detect Claude 4-Generated Text: AI Text Detection Tools and Methods

A practical guide to tools, algorithmic signals, and review workflows for detecting text generated by Claude 4 and other modern LLMs, with the reminder that AI detection is only probabilistic evidence.

2026-05-08
6 minute read
中文简体 中文繁體 日本語 Español
Technical Docs

Does F2FS Freeze an HC620 SMR Drive? Linux SMR Disk Troubleshooting Guide

Why HC620 Host-managed SMR drives may show high I/O wait and system freezes under F2FS, plus practical mount options, scheduler tuning, GC limits, and filesystem alternatives.

2026-05-08
5 minute read
中文简体 中文繁體 日本語 Español
AI Industry

miHoYo LPM 1.0 Explained: How an AI Video Model Could Reshape Game NPCs

A concise look at LPM 1.0: not a generic text-to-video tool, but a real-time character performance model for conversational agents, virtual streamers, and game NPCs.

2026-05-08
4 minute read
中文简体 中文繁體 日本語 Español
AI Industry

Canonical Ubuntu AI Roadmap: Local Inference First, No Forced Integration

A summary of Canonical's Ubuntu AI roadmap: opt-in previews after Ubuntu 26.10, AI CLI, Settings Agent, local-first inference, and pluggable backends without forced defaults.

2026-05-08
5 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Codex vs Claude Code: How to Choose Between Two Subagent Designs

A comparison of Codex and Claude Code subagent design: Codex emphasizes explicit delegation and main-session control, while Claude Code looks more like a configurable, memorable, isolated, background-capable agent workstation system.

2026-05-08
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

9Router Tutorial: Connect Claude Code, Codex, and Cursor to One AI Router

9Router is a local AI coding router. This guide covers installation, Claude Code/Codex/Cursor integration, OpenAI-compatible endpoints, token compression, model fallback, and multi-account routing.

2026-05-08
5 minute read
中文简体 中文繁體 日本語 Español
AI Tools

DeepSeek-TUI: Run a DeepSeek Coding Agent in Your Terminal

A practical overview of DeepSeek-TUI: a terminal coding agent for DeepSeek models with file editing, shell execution, Plan/Agent/YOLO modes, auto model selection, MCP, session resume, and workspace rollback.

2026-05-08
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

goose AI Agent Guide: Desktop, CLI, API, MCP, and Local Automation

A practical goose AI agent guide covering the open-source desktop app, CLI, API, MCP extensions, model providers, local automation use cases, and how it differs from simple code completion.

2026-05-08
4 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Laptop RTX 4060 8GB Local AI Guide: LLMs, Stable Diffusion, FLUX, and VRAM Limits

A practical laptop RTX 4060 8GB local AI guide covering 3B-8B LLMs, GGUF quantization, Stable Diffusion, FLUX low-VRAM workflows, Whisper, image indexing, thermals, and VRAM limits.

2026-05-08
6 minute read
中文简体 中文繁體 日本語 Español
Development Tools

How to Change the VS Code Display Language: Chinese, English, and More

A concise guide to changing the VS Code display language by installing language packs, using the Command Palette, or setting Chinese, English, Japanese, Korean, and other languages through argv.json.

2026-05-08
3 minute read
中文简体 中文繁體 日本語 Español
Hardware

AMD ROCm 7.2 + ComfyUI Compatibility Setup: Using a CUDA Alternative on Windows

A practical guide to running ComfyUI, local AI art, and video AI tools on AMD hardware with the ROCm 7.2 series on Windows and Linux, including Radeon, Ryzen AI, and CUDA-alternative tradeoffs.

2026-05-08
8 minute read
中文简体 中文繁體 日本語 Español
Hardware

RTX 5090 / 5080 AI Inference Benchmarks: Choosing for Local LLMs, 4K Video, and Real-Time 3D

A practical look at RTX 5090 and RTX 5080 specs and AI benchmarks, focusing on VRAM, bandwidth, FP4, software support, local LLMs, 4K video generation, image generation, and real-time 3D workflows.

2026-05-08
7 minute read
中文简体 中文繁體 日本語 Español
Technical Docs

DeepSeek V4 Local Private Deployment: Choosing Domestic Chips or Consumer GPU Clusters

A practical guide to DeepSeek V4 local private deployment: how enterprises can choose between data security, domestic chip support, consumer GPU clusters, inference frameworks, and cost.

2026-05-08
10 minute read
中文简体 中文繁體 日本語 Español
Technical Docs

Best Local LLMs for RTX 3060 12GB: GGUF Models, Quantization, and VRAM Tips

A practical RTX 3060 12GB local LLM guide covering the best 7B, 8B, 9B, and 12B GGUF models, Q4/Q5 quantization choices, Ollama, llama.cpp, and VRAM limits.

2026-05-08
7 minute read
中文简体 中文繁體 日本語 Español
Technical Docs

How to Draw Dashed Lines, Arrows, Curves, and Change Canvas Size in AI

A beginner-friendly guide to common AI software tasks: how to draw dashed lines, arrows, curves, and how to change canvas or artboard size in a vector design tool.

2026-05-08
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Claude Code Tips Guide: Plan Mode, Rewind, CLAUDE.md, Skills, Agents, and Plugins

A beginner-friendly Claude Code tips guide covering project startup, plan mode, permissions, rewind, terminal commands, context management, CLAUDE.md, Skills, Agents, and plugins.

2026-05-08
9 minute read
中文简体 中文繁體 日本語 Español
Development Tools

opencode Guide: Open Source AI Coding Agent Setup, Models, and Claude Code Comparison

A practical opencode guide covering setup, model providers, terminal workflow, and how this open source AI coding agent compares with Claude Code and Codex.

2026-05-08
7 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Claude Model Lineup 2026: Opus vs Sonnet vs Haiku, Which One Should You Use?

Compare Claude Opus, Sonnet, and Haiku models by coding ability, speed, cost, context window, and best use cases. Includes a simple model selection table for developers.

2026-05-08
5 minute read
中文简体 中文繁體 日本語 Español
Development Tools

uv Installation Guide: macOS, Linux, Windows, pipx, Homebrew, WinGet, and Scoop

A practical uv installation guide for macOS, Linux, and Windows, comparing the official installer, pipx, pip, Homebrew, WinGet, Scoop, Docker, GitHub Releases, Cargo, upgrades, shell completion, and uninstall steps.

2026-05-07
7 minute read
中文简体 中文繁體 日本語 Español
1 2 3 4 5 6 7 8 9 10 12
© 2022 - 2026 KnightLi Blog
记录并分享
Built with Hugo
Theme Stack designed by Jimmy