Posts tagged “llm”

CLI for Your Notes in The Archive – Automated Zettelkasten (Usage) for Programmers

Exposing your notes with a CLI can help LLM’s and you both to discover connections. The tool I wrote for The Archive essentially offers a YAML API for my Zettelkasten.

Does Bad Code in Your Context Window Misalign LLM Recommendations?

Can you effectively poison the well from which you drink your agentic Kool-Aid with the legacy code of yesteryear?

Make the pi Coding Agent Identify the Model in Commits

Custom coding agents running different models can nevertheless identify themselves during git commits. With pi, you just need to ask.

Identify Codex CLI Git Commits for an Audit Trail

Make the OpenAI Codex CLI identify itself as the author of git commits for an audit trail.

Institutional Knowledge Is a River That Can Dry Up (Don’t Fire All Your Workers)

Fire all your workers because of the potential savings from using LLMs and you may end up choking your company to death.

Xcode 26 LLM Markdown Summaries Are Actually Useful for Humans

Xcode 26 has a couple of tech docs that are intended to help LLM’s generate modern solutions to coding problems in Swift, but that also contain valuable info for us human readers.

What’s a Zettelkasten Good for in the Age of Affordable LLM’s?

Why spend time on your own knowledge and do so much manual labor when you could, you know, let the robots dance instead? I believe the answer lies in deep work and expertise.

Be Honest When Claude Code Writes Your Software

Change the commit author to your LLM/coding agent to make your git log history more honest and tell a story about collaboration.

You Don’t Need to Remember Anything Meets LLM Fans

The Scam Called “You Don't Have to Remember Anything” – That post from Zettelkasten.de blew up on Hacker News yesterday to my surprise. We will discuss this in a couple of days and let the dust settle.

Can You Really Put on Blinders If You Know There May Be Adverse Effects of Your Actions?

Is it possible to claim that you’re off the hook when it comes to questions of whether usage of GenAI should be allowed, focus on practical usage, and then that’s that? I believe that is a bit too cheap a cop-out.

Comparing Use of AI vs Learning to Code Has Nothing to Do With Knowledge

LLM code output is faster, yes, but it’s incommensurable with gaining knowledge.