Developer Tools
12 articles tagged with this topic
Three Security Gates Behind AI File Edits — The True Cost of Enterprise Agents
AI file edits pass three security gates — permission checks, optimistic locks, circuit breakers. This is why enterprise Agent adoption stays slow.
8 MCP Servers Turn Claude Into a Universal Tool — Anthropic's Standard Play
MCP is Anthropic's open standard for AI to call files, databases, and browsers. The standards race decides who controls AI's real-world gateway.
Chinese Dev Runs AI Test Pipeline — Orchestration Is What Actually Changes Work
Chinese developer chains four AI test skills into one automated pipeline. Single AI capabilities save time; orchestration changes how work actually ge
DeepSeek Agent Tutorial Hits Chapter 10 — China's LLMs Now Chase Developers
DeepSeek's Harness Agent has a 10-chapter Chinese tutorial. The shift: top LLM firms are moving from benchmark wars to developer ecosystem grabs.
AI Can Now Write Your Unit Tests — But Deciding What to Test Stays Human
A viral Juejin tutorial shows AI writing unit tests in under 20 prompts—but defining what to test still requires human judgment of business rules.
Anthropic Engineer's Four-Line Tool Hits 260K Views — Prompts Are Becoming Products
Anthropic engineer Thariq's 4-line /eli5 skill hit 260K views in hours. The real signal: prompts are becoming shippable, reusable product forms.
NVIDIA turns GPU docs into AI-callable modules — LLMs now compete on real work
NVIDIA's CUDA MCP lets AI search GPU docs and write optimized code. The takeaway: LLMs will compete on real-world work, not just intelligence.
Cursor Opens Agent Engine SDK: AI Code Editors Grab Infrastructure Turf
Cursor's TypeScript SDK opens its Agent engine to developers with local, cloud, and self-hosted runtimes. It signals Cursor's shift from tool to infra
Anthropic Adds 83 Commands to Claude Code: Terminal AI as the New Dev OS
Claude Code's 83 slash commands turn the AI assistant from a chatbox into a terminal OS, signaling AI tools' penetration into low-level workflows.
AI Wrote Bad Code, Ran rm -rf: Time to Reckon with Agent Permission Safety
A dev approved an LLM's rm -rf "fix" for its own bad bash commands. When AI has execution rights, its self-repair can be deadlier than the initial err
Cursor Opens AI Coding Core: Tools Shift From Product to Platform
Cursor's SDK opens its AI coding Agent core stack. Tools evolve from editor features to embeddable infrastructure—competition shifts from product to p
Supersimple Trims Down AI Coding Assistants — Developers Ditch All-in-One Tools
Supersimple uses a conductor to coordinate specialized agents, replacing single all-in-one assistants and signaling a shift from big to specialized AI