Catching up / Nuremberg funnels

Brain funnels are bad, right?

Yikes. I was doing so well.

My New Years resolution was to start this new blog, and then post weekly.

I got into March without missing a week. (Well, actually, I started late and then missed a couple weeks, but I always backfilled them before too much time passed.)

Then work got busy and I completely fell off the wagon.

It's a shame, because I actually have several dozen post ideas in a personal knowledge base. Most of these are little scraps of ideas, but several are fully outlined, with research, links, example code, etc. A couple have full-blown infographics.

Here's my plan for catching up.

I'm going to back off on my original goal of posting weekly. Instead, from now on, I'm targeting a blog post every other week.
That goal extends back to March. I'll prioritize forward-looking posts, but over time, I'll go back and fill in the 8 posts I've missed.

Switching gears... This post should have at least a little content; not just housekeeping.

I happened across the concept of the Nuremberg funnel recently, and I'm still unclear on whether the connotation is good or bad.

Any German-speakers want to clue us in?

Calvin and Hobbes is my point of closest approach. Brain funnels are definitely a bad thing there.

Vouching

Unlike other languages, English has no grammatical way to mark where your information came from. So we've built a colorful and extensive vocabulary for the people who exploit that loophole.

Practical tips for getting on the same page with AI

Over the last few months, I've gone through a shift in how I interact with AI agents—especially coding agents, Claude/ChatGPT chats, and Cowork sessions. I'm no longer thinking primarily in terms of instructions. Instead, I'm thinking in terms of a more abstract

What to do with your plans when the code is done

Spec-driven development is having a moment. In a nutshell: coding agents are much more likely to build the right thing if you write a detailed plan upfront. This has worked beautifully for me, and it shows up in the data. Over the last couple months, I've gone

Alignment is shifting from art to science

IMO, "do we have a shared mental model?" is one of the most powerful questions you can have in your mental toolkit. It's crucial for engineering, design, branding, relationships, teamwork, science, law, economics, markets, war, etc. It's the more practical cousin of the Turing

Read more

Vouching

Practical tips for getting on the same page with AI

What to do with your plans when the code is done

Alignment is shifting from art to science