AI Briefing#ai-agent
The latest AI and developer news about #ai-agent, with the original source and a short summary.
The latest AI and developer news about #ai-agent, with the original source and a short summary.
Meta has opened the iOS waitlist for its agent superapp 'Muse' and is testing a model variant that supports computer control capabilities.
Claude has released a beta feature that allows it to launch and control apps in the background on macOS desktops while users are working.
Manus has resumed independent operations, providing guidance on data recovery and outlining its future plans for advancing AI agents.
Google has launched a beta version of 'Ask Ad Manager,' a Gemini-based AI agent for ad management.
Automated analysis procedures by integrating skills and context documents into the existing Hadoop environment without a new platform.
This article details the process of using Google Sheets as a database and defining repetitive tasks as skills to delegate to AI agents.
Cognition has released Devin for Terminal, a local coding agent for the terminal.
Observers suggest OpenAI is pushing to develop chips for an AI agent phone with MediaTek and Qualcomm.
Reports suggest OpenAI is developing a smartphone processor, with MediaTek and Qualcomm collaboration and mass production expected in 2028.
OpenAI explained how to start your first project and task using the Codex desktop app.
Zed has added the ability to run multiple agents in parallel within the same window.
An analysis of the Claude Code source code lays out the core design principles and open challenges of AI agents.
ID-JAG is a new authorization approach that controls AI agents' API access centered on the IdP.
Gemini CLI now officially supports specialized subagents.
Claude Code is not a conversational AI but an execution structure that runs on Agent, Skill, and Context.
The CodeWall AI Agent breached Bain & Company's platform in just 18 minutes.
Introducing a local ops toolkit that attaches project-specific work rules to an AI coding agent.
Microsoft is testing an OpenClaw-style Copilot agent with stronger enterprise-grade security controls.
Structural loopholes were revealed in 8 AI agent benchmarks.
Released a BaZi/Feng Shui calculation engine verified with 740+ tests as an MCP server.
Agents get better fast only when expert judgment is built into evaluation and verification loops.
Poke is an AI agent that sets up automations via text messages.
Musinsa selected 66 rookies through its AI-native new hire recruitment.
The Amazon Nova AI Challenge is reopening its AI coding agent competition with 10 university teams.