I just tagged every post on this blog. Not with topics or categories … with a confession.

Every post now carries one of two labels: llm-generated or handcrafted. If an LLM wrote it, it says so. If I wrote it, that says so too. No hiding, no weasel words, no “assisted by AI” hedge. Binary choice. Pick one.

Why Bother?

Here’s the thing … most of this blog is for me. It’s a place to think out loud, document what I’m learning, and occasionally yell into the void about AI tooling. Whether a post was written by Claude or by me at 11pm after three cups of coffee… the ideas are still mine. The direction is mine. The “hmm, that’s interesting” moment that sparked the post? Mine.

But I think the distinction matters anyway.

We’re in this weird transitional moment where LLM-generated text is everywhere and nobody’s labeling it. LinkedIn posts, Medium articles, corporate blogs … all suspiciously polished, all using the same cadence, all somehow concluding with “In conclusion, the future is bright.” You’ve read them. You know the vibe.

I don’t want to be that guy.

The Two Tags

llm-generated … An LLM did the heavy lifting on the prose. I provided the idea, the outline, the direction, and the editorial pass. But the sentences? Those came from a model. I’ll still edit for accuracy and voice, but let’s not pretend I agonized over every semicolon.

handcrafted … I wrote it. Typos, weird phrasing, and all. These tend to be the posts I’m more personally invested in … the ones I’d actually share with someone instead of just publishing into the ether.

The Honest Part

Most of my posts are llm-generated. And I’m fine with that.

The AI Methodologies series? LLM-generated. The TIL posts? Mostly LLM-generated. This post you’re reading right now? Also LLM-generated. I’m nothing if not consistent.

But here’s what I’ve noticed: the posts I write by hand are the ones I actually care about sharing. There’s something about wrestling with your own words … deleting a paragraph three times, rewriting an intro because it sounds too corporate, realizing at midnight that your whole thesis is wrong … that makes the end result feel like yours.

LLM posts are useful. They capture knowledge, document processes, share learnings. But handcrafted posts have fingerprints on them. Literal and metaphorical.

No Judgment, Just Labels

I’m not making a moral argument here. I don’t think LLM-generated content is bad or lazy. I use these tools constantly … at work, in my side projects, on this blog. They’re force multipliers and I’d be a hypocrite to pretend otherwise.

But I think readers deserve to know what they’re getting. If you’re reading an llm-generated post, you’re getting my ideas filtered through a model. If you’re reading handcrafted, you’re getting the unfiltered version … for better or worse.

It’s a small thing. A tag. But it feels like the right thing to do when half the internet is quietly pretending that every word was lovingly hand-typed.

At least my robots are labeled.