The author shares a year of experience using AI for data work, arguing that copying someone else's workflow is pointless — what matters is learning specific techniques. He's settled on DuckDB CLI + Claude as his stack because it reduces hallucinations and keeps agents focused on actual tools instead of generating buggy code.

• AI workflows are creative, not formulaic — tips and tricks transfer better than full process replication, similar to how watching a music producer's exact steps won't let you recreate their song
• DuckDB CLI commands paired with AI agents dramatically cut hallucinations because agents understand the tool's actual capabilities rather than inventing Python code that doesn't work
• Working in a modern terminal (Ghostty) with multiple windows beats IDEs for analytics work — it's faster, gives you exactly the tools you need, and agents are already built to work with CLI tools

This article shows how macOS 27 includes a built-in LLM accessible via /usr/bin/fm that runs entirely offline and needs no account. The author tests it on an M1 MacBook Air, noting its limited memory, occasional inaccuracies, and a range of Terminal-based tricks.

• macOS 27 includes an offline, account-free LLM ("Apple Foundation Models") accessible via /usr/bin/fm in Terminal
• Runs smoothly on a base M1 MacBook Air with 8GB RAM, though it has limited memory and no awareness of current dates
• Useful for practical tasks like drafting emails, translation, summarizing Markdown, generating regex/SQL, and shell scripting help
• Prone to hallucinating dates or inventing functions when pushed beyond simple tasks

Hunk replaces plain git diff with an interactive terminal UI for reviewing full changesets. It offers split, stacked, and auto layouts, inline AI and agent annotations, sidebar navigation, watch mode, mouse support, and pager integration. You install it via npm or Homebrew and configure themes, VCS, and behaviors in a TOML config.

• Hunk turns git diff into a full interactive TUI (split/stacked/auto layouts, sidebar nav, watch mode) instead of plain text output
• It's the only tool in its comparison set (vs lumen, difftastic, delta, diff-so-fancy) offering inline AI annotations plus responsive layouts and true multi-file review
• Works as a drop-in git pager or standalone CLI, and supports Jujutsu/Sapling revsets alongside Git
• Installable via npm or Homebrew, configurable through a TOML file, and its rendering primitives (HunkDiffView) are exposed for building other OpenTUI apps

A developer ignored tmux for a decade, rebuilt their terminal workspace every morning, and lost over two hours daily. After learning six basic tmux commands, they cut setup and context-recovery time to two minutes, reclaiming hours for real work.

• Ten years of manually rebuilding terminal workspaces cost this developer roughly 2 hours 10 minutes daily (tab hunting, reconnecting sessions, rerunning commands).
• Just six tmux commands (new session, vertical/horizontal split, pane navigation, detach, attach) cover 95% of daily usage.
• After adopting tmux, morning setup dropped to two minutes with zero time lost to context recovery afterward.
• The reclaimed time went directly into shipping stalled features and clearing a backlogged review queue.