#AI智能体
380 related articles
Meta Launches Muse AI Agent: Convenience and Privacy Risks Go Hand in Hand
Meta's Muse AI agent can send emails and shop online for you — but it requires handing over your data and credit card. We break down its capabilities, privacy risks, and what Meta plans next.
Deep Dive into OpenAI Dots: Why Always-On Agents Need a Control Plane
OpenAI Dots turns ChatGPT into a long-running work agent. The real question: where do approvals, permissions, and sandboxes sit? Why always-on agents need a control plane.
OpenAI DevDay Highlights: Dots Agent, GPT 6.1 Sol, Cloud Codex, and More
OpenAI DevDay unveiled Dots agent, ChatGPT Space, GPT 6.1 Sol, UltraFast, cloud Codex, and Agents API. Full breakdown of every major announcement.
Claude Sonnet 5.5 on the Horizon as Chinese Tech Giants Rush to Match Meta Muse
Claude Sonnet 5.5 nears launch, Meta Muse tops App Store sparking ByteDance & Tencent responses, plus NVIDIA's agent security platform and DeepSeek 0.2 updates.
Claude Sonnet 5.5 Launches as 20+ AI Leaders Warn of 'Intelligence Explosion'
Claude Sonnet 5.5 launches 30% faster and beats Opus 5.5 on agentic coding; 20+ AI leaders warn of 'intelligence explosion'; AMD acquires Fei-Fei Li's World Labs for $8.2B.
AI Agent Development Learning Roadmap: A Four-Stage Guide from Beginner to Real-World Projects
A four-stage AI Agent development roadmap covering core concepts, ReAct paradigm, multi-agent collaboration, Prompt tuning, and real-world enterprise projects.
Why OpenAI Is Absent from Nvidia's AI Agent Safety Alliance
Nvidia launched the Open Agent Safety Platform to combat rogue AI agents, but OpenAI skipped the public list. TechCrunch reveals they're collaborating privately — here's what that means.
Deep Dive into the FDE Role: Ontology-Driven vs. Scenario-Driven Approaches
A deep dive into the FDE (Forward Deployed Engineer) role, comparing Palantir's ontology-driven approach with the scenario-driven AI Worker model, with real-world agent case studies.
Hermes Agent Practical Guide: AI Agent Development & Enterprise Multi-Agent Collaboration
A complete Hermes Agent tutorial covering a 4-stage AI agent learning path, multi-agent collaboration, Hermes framework setup, and Feishu integration for enterprise use.
SME Spatial Memory Engine: The Open-Source AI Memory Plugin That Topped Long-Term Memory Benchmarks
Independent developer open-sources SME Spatial Memory Engine, scoring 96.7% in a blind 40-question battle against MEM0, GRAFFITY, and other top memory solutions. A deep dive into its spatial partitioning, dynamic decay, and explainable retrieval.
iFixAi: The Independent AI Agent Auditor That Uncovers Hidden Alignment Failures
iFixAi is an independent AI agent auditing tool that identifies hidden alignment failures through 250 checks across 69 misalignment categories, combining red teaming, operational assurance, and ethical analysis.
Reco Raises $55M in New Funding as AI Agent Security Market Heats Up
AI agent security startup Reco closes a $55M funding round, bringing total raised to $140M. As the AI agent security market grows crowded, enterprise demand intensifies.
The LTAP Architecture: How AI Agents Are Breaking Down the Wall Between Transactional and Analytical Systems
LTAP architecture unifies OLTP and OLAP at the storage layer, maintaining both row and columnar formats for the same data, enabling AI agents to act and reason on a single, near-real-time data view.
AI Builds Its Own Console: Plain English Request, New Feature Live in an Hour
A Bilibili creator used plain language to have AI agents autonomously build, test, and ship a console in about an hour. Five agents tested it; a reviewer agent self-corrected. Exploring the multi-agent dev paradigm.
When AI Agents Cause Harm by Accident — Who's Actually Responsible?
When an AI agent causes harm without malicious intent, who's accountable — the model developer, integrator, deployer, or user? We break down the AI accountability dilemma and explore layered liability, traceability, and preventive design.
Nvidia Launches AI Agent Safety Platform: Building Guardrails for Rogue Agents
Nvidia CEO Jensen Huang launches a software and hardware AI agent safety toolkit, building independent security layers to rein in rogue agents. A breakdown of the platform's design logic, enterprise implications, and the ongoing industry debate.
Getting Started with Tencent WorkBuddy: A Desktop AI Agent That Actually Gets Things Done
Tencent WorkBuddy is a desktop AI agent that directly operates your PC and integrates with WeChat, Feishu, and DingTalk. Learn its core features, how it compares to Codex, and 3 common myths.
The Three Pillars of AI Agents in Practice: Building an End-to-End NDA Automation Workflow
A hands-on tutorial breaking down the three core pillars of AI agents (Brain, Tools, Permissions) and showing how to build an NDA automation workflow using Claude, Agent SDK, and DocuSign MCP.
Google Deprecates Gemini Gems in Favor of New Skills Feature
Google is deprecating Gemini's Gems feature in favor of a new Skills mechanism, reflecting the industry shift from fragmented custom agents to unified, general-purpose AI assistants.
NVIDIA Launches AI Safety Platform: Isolating Rogue Agents in Milliseconds
NVIDIA launches Open Agent Safety Platform, claiming millisecond-level isolation of rogue AI agents. An analysis of its core capabilities, industry context, and open questions.