I've been using container-use to do something like that: https://container-use.com/introduction

> Communication networks are not profitable.

Lost me on that one. Communication networks provide significant value and can be quite profitable. That's a whole industry.

>> It's possible to ask AI to write code and then read the code yourself

> Sure, but then it would not be vibecoding.

Wait, what?

Vibe-coding as originally defined (by Karpathy?) implied not reading the code at all, just trying it and pasting back any error codes; repeat ad infinitum until it works or you give up.

Now the term has evolved into "using AI in coding" (usually with a hint of non rigor/casualness), but that's not what it originally meant.

AI assisted coding/engineering becomes "vibe coding" when you decide to abdicate any understanding of what you are building, instead focusing only on the outcome

This feels like a silly semantics argument, but how is the outcome not what you are building?

tl;dr: HTTP/REST model isn't great for federated services.

There are other microservice strategies that are built around a more federated model where even having full-on recursion is not a problem.

I think the interesting thing is they saw significant improvement in computer skills, but no significant improvement in academic performance. It suggests to me that the academic program, or at least the measures from it, didn't factor in computer skills, which seems a mistake given their relevance.

I find this sentiment amusing when I consider the vast outages of the "good ol' days".

What's changed is a) our second-by-second dependency on the Internet and b) news/coverage.

Also, isn't this the promise that k8s had from the beginning... that it would be the one cloud abstraction to rule them all?

> But I will say that the shutdown of ADP is Apple being on the right side of the geopolitical fight, as inconvenient as that may be to you and me.

I don't think there's any blaming of Apple going on here. This is about dealing with the practical realities of the circumstances for people in the UK.

This bit of the FAQ was such a non-answer to their own FAQ, you really have to wonder:

>> What is the memory bandwidth supported by Ascent GX10?

> AI applications often require a bigger memory. With the NVIDIA Blackwell GPU that supports 128GB of unified memory, ASUS Ascent GX10 is an AI supercomputer that enables faster training, better real-time inference, and support larger models like LLMs.

> This bit of the FAQ was such a non-answer to their own FAQ, you really have to wonder:

You don't have to wonder: I bet they're using generative AI to speed up delivery velocity.

I guess that's the kindest possible interpretation. The other interpretation is that the answer is not a good one.

> I guess that's the kindest possible interpretation. The other interpretation is that the answer is not a good one.

If they wanted to do that, they should have just omitted the question from their FAQ. An evasive answer in a FAQ is a giant footgun, because it just calls attention to the evasion.

It's possible the FAQs were generated by one process and the answers were generated by another.

I have this problem badly enough I was interviewed for this article: https://www.wsj.com/lifestyle/workplace/work-colleague-same-...

You wouldn't believe some of the things that have shown up in my inbox.