All Posts

21 posts

In the Same Morning, OpenAI and Anthropic Both Loosened Usage Limits
4 min read
In the Same Morning, OpenAI and Anthropic Both Loosened Usage Limits

On the morning of July 12, 2026, Anthropic and OpenAI both announced usage-limit relief within less than an hour: Claude extended Fable 5 availability across paid plans and kept Claude Code weekly limits 50% higher until July 19; OpenAI temporarily removed the 5-hour usage window for Plus, Business, and Pro, optimized GPT-5.6 Sol efficiency, and reset usage. This post explains what happened and why it matters for developers.

Post News
Agent Skills: Packaging Senior Engineering Discipline Into AI Coding Agents
6 min read
Agent Skills: Packaging Senior Engineering Discipline Into AI Coding Agents

AI coding agents default to the shortest path: skipping specs, tests, security review, and other practices that make software reliable. Addy Osmani's Agent Skills packages production engineering workflows, quality gates, and best practices into 24 structured skills that agents can consistently follow from idea to launch.

Post AI
6 min read
What Is MCP: A Stable Way for Agents to Connect Tools and Context

MCP, short for Model Context Protocol, is an open protocol for connecting AI applications to external systems. It is not about making the model itself smarter. It standardizes how agents access tools, data sources, prompt templates, and business systems.

Post AI
7 min read
Claude Sonnet 5: A More Agentic Sonnet Model

Claude Sonnet 5 is Anthropic's next-generation Sonnet model, with stronger reasoning, tool use, coding, and long-horizon task execution. It narrows the gap with Opus 4.8 in agentic scenarios while covering more everyday development and knowledge-work tasks at a lower price.

Post AI
7 min read
baidu/Unlimited-OCR: A New Option for Long-Document OCR

baidu/Unlimited-OCR is Baidu's open-source long-document OCR and document parsing model, focused on converting PDFs, papers, reports, and books into Markdown. Its strengths are long-context parsing, relatively friendly GPU requirements, and open-source usability, but it is better suited to engineering workflows than simple screenshot OCR.

Post AI