Clouds and Clocks: two penguins and a bit of chaos

If you run LLMs in production—whether OpenAI, Anthropic, Gemini, or self-hosted Ollama/vLLM—you have...

On November 5, TeleAI, China Telecom's artificial intelligence institute, announced the commercial...

Ten public data-loss incidents from Claude Code, Codex, Antigravity and opencode this autumn, grouped by shell-level root cause, with the safer form for each.

Between September and October, TypeSafe, OpenAI and Cloudflare all shipped "decision model" APIs: you...

Hey everyone! I've been experimenting a lot with AI coding agents like Claude Code and Codex, and...

For a while now I have been working on Lonca, a version control system for AI agents. This post...

Many quality engineering teams have started using agentic AI testing. They connect an agent to...

A business-class trip in my demo produced four facts at the same time: the saved fields were...

An agent demo ends at the confirmation page; production starts at the first wall it is not allowed to pass. Typed stop reasons, an idempotent resume, an evidence log and a six-test matrix for the handover to a human at OTP, passkey, CAPTCH…

Six lessons from building an MCP server that lets Claude, Cursor and Codex create and render images, PDFs and video, including the bug that hid a paid render from the agent that asked for it.