#Kun
45 related articles
·3 min
ChatGPT Full-Duplex Voice Model GPT Live Launches: A Complete Revolution in Conversational AI
OpenAI launches ChatGPT Voice powered by GPT Live One — a true full-duplex voice model with real-time bilingual translation, delegation to GPT 5.5 for deep reasoning, and natural conversational flow.
Read more →
·2 min
Deep Dive into GPT-Live-1: How OpenAI Taught Voice AI to Listen Instead of Interrupt
OpenAI's new voice model GPT-Live-1 focuses on fewer interruptions, recognizing pauses, and respecting conversational rhythm. A deep dive into its technical advances.
Read more →
·2 min
ComfyUI MCP: AI Autonomously Builds Workflows, Generate Images Locally with a Single Sentence
The open-source ComfyUI MCP project uses Anthropic's MCP protocol to let LLMs like Claude directly control ComfyUI node graphs—describe needs in natural language, AI auto-builds the workflow, and renders locally on your GPU. Zero-click AI image generation.
Read more →
·6 min
DeepSeek Builds Its Own AI Chips: The Strategic Logic and Challenges Behind Compute Independence
DeepSeek is entering AI chip development, targeting compute autonomy. This article analyzes its motivations, software-hardware synergy, chip R&D challenges, and impact on China's AI vertical integration.
Read more →
·2 min
OpenAI Launches GPT-Live: Full-Duplex Voice AI That Feels Like a Real Conversation
OpenAI launches GPT-Live, a full-duplex voice AI supporting continuous interaction and intelligent task delegation for real-time translation, language correction, and parallel search.
Read more →
·4 min
The Age of AI Agents: How Version Control Must Adapt to a Paradigm Shift
AI agents are breaking Git's core assumptions. Explore the three key challenges—concurrent conflicts, history readability, and code review—and where version control is headed next.
Read more →
·7 min
The Prompt is the Platform: How AI Agents Deeply Participate in System Design and Specification
Resonate's founder proposes "The Prompt is the Platform": as AI agents generate production-grade implementations from abstract specs, engineers' value shifts to specification. A deep dive into deterministic simulation and forbidden-fruit debugging.
Read more →
·6 min
Made by Google Event Confirmed: New Pixel Phones with AI Capabilities Coming Soon
Google confirms the Made by Google hardware event in NYC, unveiling next-gen Pixel phones with new Tensor chips and deep Gemini AI integration. On-device AI gets a major upgrade.
Read more →
·3 min
GLM-5.2 Deep Dive: Million-Token Context, MIT Open Source & Full-Stack Domestic Chip Training
Deep dive into Zhipu's GLM-5.2: truly usable 1M-token context, MIT open-source strategy, full-stack Huawei Ascend training, and how it compares to Claude Opus. Includes benchmarks, use cases & pricing.
Read more →
·2 min
DeepSeek GUI Hands-On Review: How Powerful Is This Cache-First Local AI Coding Assistant?
Hands-on review of DeepSeek GUI's full agent workbench: KUN local runtime, cache-first architecture, task scheduler, and Token cost advantages for developers.
Read more →
·2 min
Claude Code + Codex in Practice: Full Breakdown of Building an AI Travel Companion Mini-Program
Developer Peter built an AI travel mini-program using Claude Code and Codex via Vibe Coding, featuring smart destination exploration, map synchronization, and auto route planning.
Read more →
·2 min
Why Is Airplane Food So Salty? The Complete Science of Taste at High Altitude
Why does airplane food always taste overly salty? It's the triple impact of low air pressure, low humidity, and noise on human taste perception at high altitude.
Read more →
Tutorials·4 min
AI Agents for Auto-Generating Excel Test Cases: From Setup to Private Deployment — A Complete Guide
Learn how to use AI agents to auto-generate Excel test cases. Covers Coze platform setup, Dify private deployment with DeepSeek + Ollama, workflow design tips, and prompt engineering for testers.
Read more →
Tutorials·2 min
Vue3 + Node.js Full-Stack Tutorial: Building an AI Travel Assistant
Learn how to build an AI travel assistant using Vue3, Node.js, and Alibaba's Qwen LLM, covering multi-turn dialogue, function calling, product recommendations, and full deployment.
Read more →
Tutorials·3 min
The Complete Guide to Claude Skills: Write Rules Once, Apply Forever — Turn AI from Generalist to Specialist
Deep dive into Claude Skills: core concepts, file structure, and practical examples. Master skill.md writing, four design patterns, and best practices for reusable AI workflows.
Read more →
Tutorials·3 min
The Complete Guide to Claude Skills: Write Rules Once, Apply Forever — Turn AI from Generalist to Specialist
Deep dive into Claude Skills: core concepts, file structure & practical examples. Master skill.md writing, four design patterns, and best practices for reusable AI workflows.
Read more →
Industry Insights·1 min
Baidu Open-Sources LoneForge Multimodal Training Framework, Achieving Up to 4.8x Training Speedup
Baidu Intelligent Cloud open-sources LoneForge, a multimodal training framework under Apache 2.0 with 20+ models supported, 15%-45% speedup, up to 4.8x acceleration, and cross-platform GPU/Kunlun chip support.
Read more →
Deep Dives·2 min
Hermes Agent Deep Dive: An Open-Source AI Digital Worker That Learns
Deep dive into NousResearch's open-source Hermes Agent framework: memory systems, skill reuse, tool calling, security, deployment guide, and multi-agent collaboration.
Read more →
Expert Opinions·2 min
Anthropic Reveals: Core Methodology for Building More Powerful Claude Agents
Anthropic shares deep insights on building Claude agents, covering Claude Code SDK, multi-agent coordination, tool design principles, and Skills injection techniques.
Read more →
Expert Opinions·3 min
AI Democratization Is a Myth: If You Can't Ride a Bicycle, an E-Bike Will Only Make You Crash Harder
Can AI programming tools really let beginners build products directly? This article uses a cycling metaphor to reveal the truth about AI democratization: tools are accessible to all, but balance can't be skipped.
Read more →