> API key not valid. Please pass a valid API key.

> Claude

- Which tiers?

> Claude Ultra (as it's now called)

- Have you purchased multiple subscriptions from the same provider (eg two Claude accounts)?

> No. Only a paid ChatGPT (Pro I think) subscription I barely use.

2) Are you using models outside (or instead) of those subscriptions? For example, pay-as-you-go APIs, OpenRouter, or locally hosted models.

Yes. Primarily OpenAI models for some projects with "AI" integration(s).

- Which models and providers?

> OpenAI. Depends.

3) What coding harnesses and interfaces are you using? Are you sticking with the default CLIs or IDE integrations, or using alternatives like OpenCode, Pi, Aider, Muse Code, or custom-built harnesses?

Straight up Claude Code.

Lots of my own Skills, Commands and my own MCP servers.

- What made you switch harnesses (if you switched)?

> Tried Codex initially. Then Claude. Never looked back.

4) Are you using any agent orchestration or swarm tools?

> No.

- For example, Munder Difflin, Gas Town, Ruflo, or something custom.

> I'm building my own specialized "bots" and "agents".

5) Are you using broader agent platforms like OpenClaw / Hermes Agent / Grok bot / Dots / Muse?

> No. Not interested.

So yes, Claude is able to write in Mu quite well -- But this isn't surprising, because I believe large language models sort of settle on the structure and patterns of languages and generalizes fairly well. So this kind of didn't surprise me at all.

If you have a pok around the site, you'll see why. Mu is deliberately very small and minimal. I've also chosen not to implement floating point arithmetic, because I wanted to see if I could get Mu programs to run on micro controllers one day, which many of them don't have FPU(s) -- especially the smaller ones.

At this point, it's mostly for fun, educational purposes and an attempt to build the smallest, but generally useful language with a good balance of dynamic performance, native code compilation, self hosting and a language that is both easy to learn and easy to understand it's design and implementation.

I call it Mu (µ) lang. You can find it at https://mu-lang.dev

Essentially µ is a language that has a dual runtime, Interpreter + Native code.

I've also experimented with building a full UNIX(ish) OS and Kernel in Mu itself. So that means, about ~2k Assembly, the rest in Mu. It's at about a 80/20 (Mu/Asm) and works fairly well!

For example, I've been working on commodifying self-hosting for the past 10 years, and whilst there are numerous attempts of the same and healthy competition, there isn't quite anything that I would consider remotely close to what I invision. With Claude Code over the past year I've been able to 10x the progress and get to the point where hopefully by end of year (2026) I'll have my first batch run and realize my dream.

It's great!

Therefore, if you start prompting and adding to the context and session history a bunch of "useless" hyperbole, slur and profanity, unless the underlying language models have been trained on such things, I find it hard to reason about what it might predict the next series of tokens should be that would be remotely useful to you.

Ultimately, I really think you need to not treat it like anything, other than a powerful inferencing tool that has a great understanding of a very large corpus it has been trained on and has modelled very well. Use it to your advantage, there is no point in rudeness or profanity, it has no feelings, it isn't intelligent. At worst you risk garbage output.

What if it were you or me (I'm a native English speaker). Why if the tables were turned the other way around? I'm not even sure how I'd honestly be able to communicate with a person say from France, as I know a lick of French really, so I'd be reaching for some kind of translator, anything really. How do I avoid the wrath of those that would ben me over "AI Slop"?!

Marko looks like a mix of at least 3 languages. No thanks!