Impressions from visiting OpenAI, Anthropic, & Cursor
A peek into where software engineering is headed from inside the sector’s leading AI labs. Agents running in the cloud are a major trend, while coding harnesses are spreading beyond the craft
Claude Codeでコーディングやデータ分析をするときのトークン消費を、プロンプトキャッシュの仕組みから理解して減らすための技術解説。前方一致のキャッシュ機構、TTL別のキャッシュコスト、usageでの検証方法、キャッシュを壊すサイレント無効化まで、公式ドキュメントの参照URL付きでまとめました。
Oak is the agentic substrate for software development: the version-control and storage layer autonomous coding agents build on. Mount large repos without a full clone, branch per task, snapshot up to 95% faster than git, and bring your own agent: Claude Code, Codex, Cursor.
tuicr is a TUI for code review with vim keybindings. Scroll a GitHub-style diff, leave line-level comments, then push a real PR review to GitHub, or copy structured markdown for your coding agent.
A native Mac terminal for orchestrating AI agents. Sessions that never die, parallel git worktrees, one-tap launches, and Unpeel Sessions MCP. $59 first year, then 50%.
Review your AI agent's code changes in a browser with inline comments and round-to-round diffs. Comment on specific lines, the agent fixes them. Single binary, works locally, any agent.
npm now adds a temporary, preventive safeguard for high-impact accounts—those responsible for the registry’s most widely used packages—whenever it detects a sensitive account change, strengthening protection against account-takeover attacks. When…