Plockepinn in Swedish, approximately "pickastick".

Edit: thought I read it was of Scandinavian origin, hence my comment. But Wikipedia said european origin. Well well.

I suspect it was invented the first time a parent dropped a pile of sticks because their bored kids were distracting them. “Ok kids, new game, pick those sticks up as quietly and tediously as possible.”

In the US, it was a game called "pick up sticks", and it was tedious and sometimes impossible.

So, this method is well-named at least! :)

Actually a pretty good metaphor.

I don't think it is that simple. Innovation can be found on several levels, from the lowest next-token level up to the higher level of new ways of combining things. Surely LLMs can produce code that on the whole does something completely new, even if on a syntactical level it has all been seen before?

We only have a couple dozen letters, still it is possible to write new poetry.

I have heard "cloud code" many times from colleagues who do not really know what either cloud OR Claude Code is more than "stuff we should use".

Whisper voice to text very rarely manages to make it Claude, here's some examples and I am not trying to make it bad

Lord code, close code, Clawed code, load code, Claude Chatbot, Claude Code, cloud code.

I wish it had a better name. We know it was named after Claude Shannon. A very nerdy choice rather than a marketeer.

Time really goes by. I read "article from 26 years ago" as: why would you post an article from the early 80s?

I feel old.

The article itself is about an event that happened in the late 80’s.

Agree.

No matter how useful AI is and will become - I use AI daily, it is an amazing technology - so much of the discourse is indeed a solution looking for a problem. I have colleagues suggesting on exactly everything "can we put an MCP in it" and they don't even know what the point of MCP is!

I agree completely.

To me it seems you and many others are lost in the weeds of constantly evolving tooling and strategies.

A pretty basic Claude Code or Codex setup and being mindful of context handling goes a long way. Definitely long enough to be able to use AI productively while not spending much time on configuring the setup.

Staying on top of all details is not necessary but in fact counter productive, trust me.

I don't need to trust you, I've done my own testing and using newer tooling features is dramatically better than not. One of the things about the AI tooling is that it's very inexpensive to run experiments (this week I've had it build a particular tool in Python, Go, Rust, and Zig, for example).

Using skills, multiple models, MCPs and agent teams is significantly improving the results I'm seeing in real world problems.

You haven't really given me any reason why I should trust you, but I'll tell you it's going to be hard for me to trust advice that contradicts my test results.

That is an LLM right there. Wow.