Read source code together, write articles together, and enjoy spicy hot pot together.
The article walks through configuring a custom model in Claude Code, installing the claude‑tap plugin, launching the tool, sending the message “Hello”, and then dissecting the resulting request to reveal token counts, latency, tool list, system prompts, message payload, and a lingering cache issue.
The article argues that, like the container‑shipping revolution, generative AI belongs to a mature phase of a larger ICT wave, offering limited upside for investors while the real wealth accrues to downstream users and established firms that can exploit cost reductions.
A benchmark of Redis, Memcached, DragonflyDB, and Cashews using the same FastAPI workload reveals that Redis falls behind on latency, throughput, and memory efficiency, while DragonflyDB and Cashews offer superior performance and developer experience for Python caching.
Long Claude Code sessions quickly become noisy as every grep, find, and ls call stays in the main context, but using sub‑agents—including the built‑in Explore and Plan agents and the CLAUDE_CODE_FORK_SUBAGENT flag—isolates work, returns only concise summaries, and lets you monitor activity with a context‑timeline hook.
The author reflects on automating reading with AI, distinguishing information gathering from thinking exercises, and proposes a three‑question framework to decide when automation adds value versus when personal reading is essential, ultimately choosing to limit AI to pre‑ and post‑reading tasks.
The article examines the recent Claude performance controversy, showing that engineering adjustments to inference parameters, cache handling, and system prompts rewrote the model’s behavior, making it answer faster but think shallower, leading users to perceive a degradation despite no official model downgrade.
The article compares direct API calls, CLI tools, and the Model Context Protocol (MCP) for agent integration, explains MCP's token overhead, presents two token‑reduction strategies, and outlines design principles for building high‑availability MCP servers to maximize agent utility.
AI‑powered coding tools let designers turn ideas into runnable demos instantly, but true deliverables require clear problem definition, state coverage, error handling, maintainability, and production stability, prompting a shift toward expressive, validation, and delivery coding while emphasizing engineering understanding and robust design systems.
The article shows how to use OpenAI's Images 2.0 model to generate usable pixel‑art game sprites by supplying a 1024×1024 grid reference, scaling, cleaning, background removal, and assembling a 2×5 sprite sheet, while detailing common pitfalls and concrete fixes.
This guide walks you through installing Ghostty on macOS, adjusting security settings, using Homebrew or direct download, customizing themes, fonts, and window behavior, and leveraging its keyboard shortcuts for split panes, providing a modern, powerful alternative to the default Terminal.
