AI Dev Stack

Sign in Subscribe

ai-coding

Claude Code Gets Sandboxing: 84% Fewer Permission Prompts

Claude Code Gets Sandboxing: 84% Fewer Permission Prompts

Anthropic shipped sandboxing for Claude Code that cuts permission prompts by 84%. OS-level isolation creates hard boundaries for filesystem and network access, letting Claude run autonomously within defined limits while blocking prompt injection attacks.

Code Execution with MCP: How Anthropic Cuts Agent Costs by 98%

Code Execution with MCP: How Anthropic Cuts Agent Costs by 98%

Anthropic shows how code execution with MCP cuts agent token usage by 98.7%. Instead of loading thousands of tool definitions upfront, agents discover tools on-demand and process data locally.

Claude Can Now Search 1,000+ Tools Without Blowing Its Context

Claude Can Now Search 1,000+ Tools Without Blowing Its Context

Anthropic shipped Tool Search Tool, Programmatic Tool Calling, and Tool Use Examples. Tool Search cuts token usage 85% by discovering tools on-demand. Programmatic Calling orchestrates workflows in code, eliminating inference overhead. Examples teach correct usage patterns schemas can't express.

How Anthropic Solved the Long-Running Agent Problem

How Anthropic Solved the Long-Running Agent Problem

Anthropic cracked the long-running agent problem with a two-part harness: an initializer that scaffolds 200+ features, and a coding agent that works incrementally with git-based progress tracking. Here's how it works.

How Anthropic Actually Builds Evals for AI Agents That Ship

How Anthropic Actually Builds Evals for AI Agents That Ship

Anthropic's playbook for building AI agent evaluations that actually work. Start with 20-50 real failures, combine deterministic and model-based graders, and read the transcripts. The teams that invest early ship faster.

Anthropic's Hiring Test Can't Beat Claude Anymore

Anthropic's Hiring Test Can't Beat Claude Anymore

Anthropic's performance engineering take-home has been defeated twice by its own Claude models. The team redesigned it three times, eventually abandoning realism for deliberately weird puzzles. Here's what they learned about AI-resistant technical evaluations.

Anthropic Built a C Compiler with 16 Parallel Claudes

Anthropic Built a C Compiler with 16 Parallel Claudes

Anthropic researcher ran 16 parallel Claude instances for two weeks to build a 100,000-line C compiler from scratch. It compiles Linux, costs $20k in API calls, and reveals where autonomous agent teams hit their limits.