Anthropic says Claude Code can create task-specific workflows that spawn subagents for complex work, with higher token costs and open questions.
Browsing Category
General
175 posts
When One Agent Isn’t Enough: Claude Now Builds Its Own Team of Agents on the Fly
Anthropic says Claude Code can now create task-specific workflows that coordinate subagents for complex work.
The Eye Over the City: How Wide-Area Motion Imagery Works — and Where It Goes Blind
Thorsten Meyer AI’s July 1 briefing details WAMI’s city-wide tracking power, AI dependence, radar gaps and legal risks.
The Eye Over the City: How Wide-Area Motion Imagery Works — and Where It Goes Blind
A July 2026 briefing explains how WAMI tracks citywide movement, where it fails, and why courts and AI oversight matter.
The Delegation Ladder: The Four Agentic Loops, and What Each One Lets You Stop Doing
Anthropic’s Claude Code team outlined four agentic loop types, reframed by Thorsten Meyer AI as a delegation ladder for AI work.
The Delegation Ladder: The Four Agentic Loops, and What Each One Lets You Stop Doing
Anthropic’s Claude Code team defines four AI agent loop patterns, offering a clearer map for when to delegate checks, goals, triggers and prompts.
Twice the Price, 5.7% More Intelligence
Anthropic’s Fable 5 costs twice Opus 4.8, while third-party benchmarks show a 5.7% Intelligence Index gain.
This surprised us about the merchandise at Trump’s state fair
Official fair merchandise omits Donald Trump’s image, despite his rally presence and related collectibles. Details remain unclear why.
Douglas Murray: What Really Makes ‘Citizen Vigilante’ So Dangerous
Douglas Murray criticizes the film ‘Citizen Vigilante,’ highlighting its dangerous portrayal of violence and migration issues, raising concerns about its societal impact.
A Skill Is a Folder, Not a Prompt: What Anthropic Learned Running Hundreds of Them
Anthropic says hundreds of Claude Code Skills show how folder-based agent workflows can preserve team knowledge and improve checks.