AI agents — Page 10
228 stories tagged AI agents.
China's AI Agents Are Getting Scary Good—And Cheap
ByteDance and Alibaba just dropped AI agents during Lunar New Year. The timing matters, the tech matters more, and the cost efficiency changes everything.
OpenAI’s Codex vs Anthropic’s Opus: Two Different Agent Philosophies
OpenAI’s Codex vs Anthropic’s Opus: Two Different Agent Philosophies
OpenAI's Codex 5.3 and Anthropic's Opus 4.6 represent fundamentally different visions for AI agents—one built for delegation, the other for coordination.
OpenAI Just Hired OpenClaw's Creator. Here's Why.
OpenAI Just Hired OpenClaw's Creator. Here's Why.
Peter Steinberger's journey from viral open-source AI agent to OpenAI reveals the real battle happening in AI right now—and it's not about models.
AI Agents Are Getting God Mode—And That's a Problem
AI Agents Are Getting God Mode—And That's a Problem
IBM's Grant Miller explains how AI agents with elevated permissions create security nightmares—and what actually works to prevent privilege escalation.
GitHub's AI Agent Explosion: 30 Tools Reshaping Dev Work
GitHub's AI Agent Explosion: 30 Tools Reshaping Dev Work
From $10 AI agents to browser-based coding assistants, GitHub's latest trending repos reveal how developers are hacking their own workflows with AI tools.
When AI Bots Started Scheming, We Learned More About Us
When AI Bots Started Scheming, We Learned More About Us
Moltbook's viral AI agent drama revealed less about artificial intelligence and more about human fear, gullibility, and our appetite for digital theater.
Anthropic's AI-Built C Compiler: Engineering Feat or PR Stunt?
Anthropic's AI-Built C Compiler: Engineering Feat or PR Stunt?
Anthropic let 16 Claude agents build a C compiler over two weeks. It compiled Linux and ran Doom—but the methods raise questions about what 'AI-built' means.
One AI Agent Saved $4,200, Another Spammed 500 Texts
One AI Agent Saved $4,200, Another Spammed 500 Texts
OpenClaw reveals what happens when 145K developers build AI agents: brilliant car negotiations, catastrophic database wipes, and everything in between.
Agent Zero's Plugin Future: Making AI Agents Modular
Agent Zero's Plugin Future: Making AI Agents Modular
Agent Zero v0.9.8 brings Claude Skills support, Git integration, and a redesigned UI—but the real story is what's coming next: a full plugin architecture.
Warp's Oz Platform: When Engineers Eat Their Own Agent Food
Warp's Oz Platform: When Engineers Eat Their Own Agent Food
Warp built Oz to run AI agents in the cloud. Then their engineers started using it internally. What happened next reveals something interesting about agent adoption.
GitHub's AI Agent Security Crisis Has 30 New Answers
GitHub's AI Agent Security Crisis Has 30 New Answers
Developers are building solutions to AI's biggest problems: spam PRs, memory loss, and security nightmares. Here's what's actually working.
Zero Trust Security Faces Its AI Agent Test
Zero Trust Security Faces Its AI Agent Test
AI agents that can buy things and spawn sub-agents need security frameworks that assume breach from the start. Zero trust principles are getting a second life.
Software Lost $400B Last Week. Should You Care?
Software Lost $400B Last Week. Should You Care?
The SaaS apocalypse wiped out $400 billion in market value. Here's what's actually happening beyond the panic—and what it means for software's future.
This Dev Automated His Entire Workflow With Claude & Linear
This Dev Automated His Entire Workflow With Claude & Linear
Kenny Liao built a system where AI handles his entire dev cycle—from planning to PR reviews. Here's how he ships code while barely touching his keyboard.
This Developer Spent $20K Building an AI Company That Never Sleeps
This Developer Spent $20K Building an AI Company That Never Sleeps
Alex Finn invested $20,000 in local AI models to create a 24/7 autonomous digital workforce. Here's what happened when the API costs disappeared.
Agent Zero Challenges AI Privacy Assumptions
Agent Zero Challenges AI Privacy Assumptions
Open-source AI agent Agent Zero offers full privacy and multi-model efficiency while running on your own server. Here's what that actually means.
TypeScript Bash Implementation Cuts AI Token Costs by 95%
TypeScript Bash Implementation Cuts AI Token Costs by 95%
JustBash runs Bash commands in TypeScript without infrastructure, reducing AI agent token usage from 133,000 to 6,000 in real-world tests.
Anthropic Bet on Teaching AI Why, Not What. It's Working.
Anthropic Bet on Teaching AI Why, Not What. It's Working.
Anthropic's 80-page Claude Constitution reveals a fundamental shift in AI design—teaching principles instead of rules. The enterprise market is responding.
OpenClaw Raises Questions Nobody Wanted to Answer
OpenClaw Raises Questions Nobody Wanted to Answer
An Austrian hobbyist's open-source AI project is forcing developers to confront what happens when your assistant calls you first—and won't stop calling.
New AI Agent Nanobot Challenges Industry With 99% Less Code
New AI Agent Nanobot Challenges Industry With 99% Less Code
Nanobot's 4,000-line codebase versus OpenClaw's 430,000 raises questions about whether AI complexity serves users or just creates technical debt.