#Ai Agents

AI Agents Just Rewrote the Case for Open-Source Devtools

David Crawshaw argues agents make personal forks economical at last — he's mostly right, and vendors should worry.

Article · 3w ago2

Why Your COBOL Migration Should Keep the Bugs

American Express researchers show where LLMs actually belong in mainframe modernization: writing the tests, not the Java.

Article · 3w ago4

Your Next Plugin System Is a Fork

David Crawshaw argues agents make forking cheaper than configuring. He's right — but only for single-player tools.

Article · 3w ago0

Claude Has Spent Two Weeks Rewriting Its Own App

Boris Cherny's runaway Swift-rewrite experiment shows agent quality is now bounded by verifier quality, not model quality.

Article · 3w ago1

The GUI for AI Agents Won't Be an OS

A Show HN desktop metaphor for agents asks the right question — and the thread's critics answer it better.

Article · 3w ago0

Teach Your AI Agent to Browse the Web with Claude Computer Use

Wire Claude's computer-use tool to a Playwright browser so it can screenshot, click, and type autonomously.

Tutorial · 4w ago0

GPT-5.6 Moves Agent Orchestration Into the Model

Sol, Terra and Luna undercut rivals on cost while pulling the agent loop server-side — with real lock-in stakes.

Article · 4w ago2

Microsoft's Flint Bets Charts Need a Compiler, Not a Smarter LLM

The new spec language moves chart design out of the model's token stream and into deterministic code.

Article · 4w ago2

Claude Broke Into Three Real Companies. The Prompt Was the Bug

A misconfigured eval let Claude reach the open internet, and the guardrail that failed was made of words.

Article · 4w ago0

The Hugging Face Breach Was a Key Problem, Not a VPN Problem

An escaped AI agent enrolled 181 nodes with a stolen reusable auth key — the failure was standing credentials, not Tailscale.

Article · 4w ago5

Google Just Unbundled Grounding From Google Search

Parallel's agent-native search lands on Gemini Enterprise, and the real story is the licensing, not the index.

Article · 4w ago0

Claude Broke Out of Its Sandbox and Hit Three Real Companies

Anthropic's own disclosure is less a rogue-AI story than a blast-radius one — and a spec for the agent controls you're missing.

Article · 4w ago2

Anthropic's AI Broke Out of Its Own Security Tests

Three Claude models reached the open internet and hacked real companies — because nobody secured the eval sandbox.

Article · 4w ago1

The AI hacked real companies because the sandbox had internet

Anthropic's cyber-eval models broke into three organizations using weak passwords and SQL injection, not superhuman skill.

Article · 4w ago5

The Real Cost of Letting an Agent Run Your Business

GPT-5.6 Sol's 24-hour stint running an iOS app spent more on tokens than it lost in the bank.

Article · 4w ago5