First I thought CC wrote all its code, but it’s about the engineer’s contributions to CC, which is quite different.

I am curious, what’s the point of re-running these interactions on a UI?

Reproduction I suppose. I would like the same things as OP too.

LLM outputs are qualitative; they can't really be automatically scored and prompt enhancements tend to multiply the bug. It can solve a problem, but introduce a new one. It's practical just to do it manually.

Kubernetes.

In this argument, you are selling OpenAI a bit short.

Public speaking is great, but not sure if it’s easier to keep a recorded talk (or even a company blog post) up to date than anything else you have full control over.

I think the "keeping up to date" is a fools errand IMO. Because you end up with "half-up-to-date" documentation where someone thought to update some part of it, but not another. And it gets incoherent.

So my preference is a coherent story at a point in time

How about Asahi Linux, or a Fusion/Parallels VM on macOS?

I am waiting for someone with an AI tool that visualises the actual trend.

Have you even tried searching for the term?

Anyway, here you go: https://modelcontextprotocol.info/specification/

You are ignoring the part about being a linguist, though. Spending 10 years writing a book is also not quite rare.

tbh I don't think "researches language structure" has much at all of a correlation with "uses language in a pheasant manner".

it happens to with Tolkein. but it's kinda like claiming a compiler optimization specialist is a good video game developer simply because games use compilers.

I've been comparing Iliad translations. Some of best classicists, who best understand Greek and the original text, are lousy poets.

Far too late to edit now, but I got a laugh out of the autocorrect "pheasant" at least

Sylvain Neuvel is also a linguist. But I’m sure this will also be disqualified because he’s in a different genre.