94 related articles

Tencent Hunyuan and Tsinghua jointly release DiscoBench, the first benchmark evaluating search agents' dynamic ambiguity clarification. Covering 463 ambiguity instances across 11 domains, it reveals real weaknesses of mainstream LLMs.

An in-depth hands-on review of Zhipu AI's flagship GLM-5.2: 1M-token context, strong coding, mature agent workflows—at one-fifth the price of top frontier models. Covers website testing, Cursor integration, MCP tooling, and production migration.

Andrew Ng and LangChain CEO Harrison Chase present AI Agents in LangGraph, covering five core agent design patterns and LangGraph's graph-based framework for building cyclical agentic workflows.

Andrew Ng and LangChain CEO Harrison Chase's AI Agents in LangGraph course covers five agent design patterns and LangGraph's graph-based framework for building cyclical AI workflows.

Anthropic releases Claude Sonnet 5, its most agentic mid-tier model with planning, browser/terminal tool use, and autonomous execution—bringing flagship Agent capabilities at significantly lower cost.

Anthropic releases Claude Sonnet 5, its most agentic Sonnet model yet. With planning, browser/terminal tool use, and autonomous execution, it brings flagship Agent capabilities to mid-tier pricing.
Perplexity Integrates Forge Private Ma…
Perplexity integrates Forge Global private market data into Perplexity Computer, enabling direct queries on pre-IPO valuations. A deep dive into the strategy, data moat logic, and AI's push into professional financial research.

Anthropic hosted a Build Day hackathon in Cerebral Valley, inviting top developers to demo AI apps built on Claude. Analysis of developer ecosystem strategy and industry competition.

Perplexity CEO announces Perplexity Computer will integrate all business connectors, enabling users to create and run companies from scratch with AI.

Perplexity integrates Deep Research as a native skill in Computer, enabling automatic invocation without manual mode switching. Analyzing the Agent Harness design philosophy and AI capability fusion trends.

June 2, 2025 AI roundup: NVIDIA's 550B Nimitron 3 Ultra, xAI Composer 2.5, Anthropic & ZhiPu IPOs, OpenAI's agentic OS prototype, and key advances in agents, compute infrastructure, and open source.

A deep dive into an indie developer's AI programming workflow, covering Codex, Ghost database management, Create Skills context system, and MCP servers for maximum efficiency.

Mastering AI tools doesn't equal making money. This article breaks down the three-layer AI wealth model: LLM prompting, automation workflows, and agent collaboration, plus the MAPS framework and Three R's Rule.
Product ReviewsIn-depth review of 11 AI Agent tools including ChatGPT Agent, Manus, and Claude Code, covering office work, academic writing, coding, and video creation scenarios.
Tech FrontiersClaude plans routes for NASA's Perseverance rover, Windsurf launches Arena Mode for in-IDE model comparison, SenseTime open-sources multimodal reasoning models, and Anthropic research reveals pros and cons of AI-assisted learning.
TutorialsLearn how Zion's no-code platform lets you build AI agents via drag-and-drop, with a hands-on prompt optimization assistant tutorial covering knowledge base integration, UI building, and API access.
TutorialsA detailed guide on how indie developers can use AI tools to build fully automated marketing systems—from MCP research to Skills systems to automated content production and traffic engines.
Industry InsightsDeep dive into MCP's cloud repositioning strategy, how Anthropic cuts token costs by 85% with Tool Search and code sandboxes, and 12 Agentic patterns for production-grade AI Agents.
Product ReviewsPair AI natively integrates 6 AI coding tools—Roo Code, SuperMaven, Perplexity, Memo, Continue—into one editor starting at $15/month, competing with Cursor and Windsurf.
TutorialsComplete guide to deploying OpenClaw with Sonnet 4.6 on VPS: low-cost enterprise AI agent setup with Slack integration, heartbeat automation, and team collaboration.