Ai Agents
122 stories tagged Ai Agents.
The Karpathy Loop: When AI Runs 700 Experiments Overnight
Andre Karpathy's AI agent ran 700 experiments while he slept, found bugs he missed, and cut training time 11%. Here's what that means for everyone else.
Why Your AI Agent Sits Idle After Installation
Why Your AI Agent Sits Idle After Installation
Installing an AI agent takes 10 minutes. Making it actually useful takes 40 hours. Here's why the industry keeps solving the wrong problem.
Harness Engineering: The New Frontier in AI Development
Harness Engineering: The New Frontier in AI Development
AI companies are shifting focus from better models to better infrastructure. Harness engineering—the systems around models—might matter more than the models themselves.
Anthropic's Claude Code Update: AI Agents Get Planning Tools
Anthropic's Claude Code Update: AI Agents Get Planning Tools
Anthropic released Claude Code v2.1.92 with Ultra Plan for transparent AI project planning and Managed Agents for deployment without infrastructure.
Amazon Built AI Agents for Millions. Here's What Actually Works
Amazon Built AI Agents for Millions. Here's What Actually Works
Amazon's AI Product Leader shares hard-won lessons from building multi-agent systems serving millions. Spoiler: human oversight isn't a failure mode.
Anthropic's Managed Agents: What Makes Them Different
Anthropic's Managed Agents: What Makes Them Different
Anthropic's Claude Managed Agents let you build AI agents without code. Here's what the architecture reveals about where agent development is headed.
Claude's New Monitoring Tool Fixes AI's Expensive Idling Problem
Claude's New Monitoring Tool Fixes AI's Expensive Idling Problem
Anthropic's Claude Code Monitor lets AI agents sleep instead of burning tokens checking for problems that don't exist. It's smarter, but is it new?
When Your AI Agent Ships Code While You Sleep
When Your AI Agent Ships Code While You Sleep
Hearth AI founder Ashe Magalhaes builds entire products in hours using AI agents. What does this mean for engineering work and software development?
OpenAI and Anthropic Face Their Monetization Reckoning
OpenAI and Anthropic Face Their Monetization Reckoning
As OpenAI and Anthropic prepare for IPOs, both companies are making hard choices about compute resources and pricing. The AI industry's profitability problem is here.
Composio Wants to Be the Universal Adapter for AI Agents
Composio Wants to Be the Universal Adapter for AI Agents
Composio promises to connect AI agents to 1,000+ apps via CLI. But does abstracting integration complexity actually solve the right problem?
How One Developer Automated Marketing With AI Agents
How One Developer Automated Marketing With AI Agents
Brian Casel built four AI agent skills to handle his marketing. Here's what that actually looks like when you open the hood and examine the process.
The AI Agent Infrastructure Nobody's Watching Yet
The AI Agent Infrastructure Nobody's Watching Yet
A new infrastructure stack is being built for AI agents—six layers deep, billions in funding, and most builders can't tell what's real from what's hype.
Agent Zero's Tutorial Raises Automated Access Questions
Agent Zero's Tutorial Raises Automated Access Questions
Agent Zero's communication integration tutorial demonstrates a growing regulatory gap: automated agents accessing messaging platforms without clear legal framework.
AI Agents Promised to Do Your Work. They Can't Yet.
AI Agents Promised to Do Your Work. They Can't Yet.
Wall Street lost $285B betting on AI agents that would replace SaaS tools. But the tech that triggered the panic still sleeps when you close your laptop.
Google's Agent Skills Update Just Fixed AI's Biggest Flaw
Google's Agent Skills Update Just Fixed AI's Biggest Flaw
Google's ADK now uses progressive disclosure to stop AI agents from loading unnecessary instructions. Here's why that matters for everyone using AI.
Anthropic's Claude Code Leak Reveals Unglamorous Truth
Anthropic's Claude Code Leak Reveals Unglamorous Truth
The Claude Code leak shows what actually makes AI agents work at scale: boring infrastructure, not flashy features. Two leaks in one week raise questions.
AI Agents Are Getting Persistent—And That Changes Everything
AI Agents Are Getting Persistent—And That Changes Everything
Anthropic's Conway, Z.ai's GLM-5V-Turbo, and Alibaba's Qwen 3.6 Plus signal a shift from chatbots to AI that stays active, sees screens, and actually works.
Paperclip Wants You to Run a Company With Zero Humans
Paperclip Wants You to Run a Company With Zero Humans
Open-source tool Paperclip promises to orchestrate AI agents into a working company. David Ondrej demonstrates the setup—and the gaps between vision and reality.
AI's Second Moment: When Agents Go From Hype to Reality
AI's Second Moment: When Agents Go From Hype to Reality
Enterprise AI shifted from pilots to production in Q2 2026, with agentic systems driving $650B in capex and sparking unprecedented political battles.
Claude Code + Paperclip: Running Companies With AI Agents
Claude Code + Paperclip: Running Companies With AI Agents
Julian Goldie shows how Claude Code and Paperclip create AI agent companies with org charts, roles, and budgets—no human employees required.