Happy National Burrito day. I am at a food truck …. Getting a burrito after I discovered today ISTHE Day

Don’t over salad

Anywhere, 🇺🇸

Always at the ready

I'm a rebel. I don't optimize my LinkedIn Post.

trellises and vines pergula espalier jasmine passionflower honeysuckle wisteria grapevines hydrangea cedar redwood blacklocust apples pears fig trees

Python refactor for poetry encoding project. Want to see if I can create a new standardized way of doing it. LMK if you think this is interesting.

What if we are the Symbiote? What would we be? #finishthatpoem

OK. Figured out a couple of ways to encode in visual layer. This is Whitman's "O Captain! My Captain!". Going to work on a rectangle based structure next.

The meat shall inherit the earth

This is all insane and also thank goodness there are no downsides to burning or geopolitical barriers to accessing LNG. /s

These are (public domain) #poems. Encoded with LSB steganography. LMK if you want me to do yours.

.

I'm Just Going to Use Zed: https://llbbl.blog/2026/03/18/im-just-going-to-use.html

Voice-to-Text in 2026: The Tools and Models Worth Knowing About: https://llbbl.blog/2026/03/17/voicetotext-in-the-tools-and.html

How Smart People Are Using Claude Code Skills to Automate Anything 🚀 Build agentic systems that run your business: skool.com/scrapes Don’t miss the next build - www.youtube.com/@simonscr…

Polar Loop | Screen-Free Wearable Health Band & Fitness Tracker | Polar USA Track sleep, recovery, and activity—without screens, distractions, or subscriptions. POLAR Loop is a wearable fitness band that helps you track and improve your well-being, fitness, and daily performance.

Everything Is Eventually a Database Problem: https://llbbl.blog/2026/03/16/everything-is-eventually-a-database.html

Your Context Window Is a Budget — Here's How to Stop Blowing It: https://llbbl.blog/2026/03/15/your-context-window-is-a.html

I got tired of plaintext .env files, so I built LSM. lsm exec will inject secrets at runtime so they never touch the filesystem. Doppler’s idea, minus the monthly bill. How are you managing local secrets?

I switched to mise for version management a month ago. No regrets. No more brew upgrade breaking Python. Built-in task runner replaced some of projects that were using Makefiles. Still juggling nvm + pyenv + rbenv?

I know what happened the day Lothar fell.

I wrote about why you should stop using pip. Poetry or uv. Pick one. pip has no lockfile, no dependency resolution worth trusting, and no isolation by default. Have you moved to uv yet? Still happy with poetry? How’s it going?

😑 Amazon Prime Video no ads price going up. I already hate that we occasionally “have to” pay when we are watching 30% ads on an hour program. Flock that.

I wrote about when to reach for Python over Bash. Most veterans put the cutoff at 50 lines. If you’re writing nested if statements in Bash, you’ve already gone too far. Where does Go fit in though? Overkill for scripts?

With AI agents, the cost of writing tests is approaching zero. Five words: “write tests on new code.” The excuses are running out. Are you verifying the tests your AI writes, or just trusting the green checkmarks?

I compared npm, Yarn, pnpm, and Bun. TLDR version: pnpm wins for most teams, Bun wins if you’re already on the runtime. Has anyone switched their whole team to Bun yet? How’d that go?

I wrote about securing node_modules. Socket, Snyk, Dependabot — each catches different things. Hopefully answering when to use AI to rewrite simple deps you barely use. Anyone want to build that CLI?

Wrote a guide on writing a good CLAUDE.md. Takeaway: keep it under 200 lines. Every line loads into context every session, so bloat costs real tokens. How are you handling multiple AI context files across tools?

When to Use Python Over Bash: https://llbbl.blog/2026/03/10/when-to-use-python-over.html

The void prays on fear

My friend is level 87 and needs 90 to progress in Midnight

Why Ghostty Is My Terminal for Agentic Work: https://llbbl.blog/2026/03/09/why-ghostty-is-my-terminal.html

Overwatch Stadium vs World of Warcraft Midnight

Python: If your CLI tool uses print() and gets called as a subprocess by Claude Code, the output now gets swallowed. The parent process captures it. Structured logging will fix it.

Mountains of men

Why Ghostty Is My Terminal for Agentic Work: https://llbbl.blog/2026/03/07/why-ghostty-is-my-terminal.html

I had to look it up, there have now been three gulf wars in my lifetime 🤦🙁

I didn't even know this was a thing... "centralized email signature management"

Tell me your entire job is dealing with Enterprise only problems without telling me what the Title is.

How to Write a Good CLAUDE.md File: https://llbbl.blog/2026/03/06/how-to-write-a-good.html

Claude Code Skills vs Plugins: What's the Difference?: https://llbbl.blog/2026/03/05/claude-code-skills-vs-plugins.html

Claude Code Now Has Two Different Security Review Tools: https://llbbl.blog/2026/03/04/claude-code-now-has-two.html

@github.com Seems to be having major issues for the last ~40 minutes. It's not you. #GitHubOutage

Ever wanted your CLAUDE.md to automatically update from your current session before the next compact? There’s a skill for that and it’s been helpful. In case you missed it, here’s a link to the skill: autoskill

Managing Your Context Window in Claude Code: https://llbbl.blog/2026/03/02/managing-your-context-window-in.html

Built a thing: Chord Compass — an interactive circle of fifths that lights up chord relationships when you click a key. Load preset progressions like I–V–vi–IV, hit play, hear them back. It looks like a brass compass from an old music theory textbook and I love it.

I built Scale Lab — pick a root note, choose from 14 scales and modes, and watch the notes light up on a piano keyboard. Hit play to hear them ascend. Just a bit of music theory fun. Enjoy!

I published an Agentic Maturity Model on GitHub, a mental framework for thinking about and categorizing AI tools. It’s open to contributions and I’m looking for coauthors. Agentic Maturity Model