I assume the target audience for the question is developers. That will generate many responses along the lines of ”just use a CLI”.

The current, main driver I see for MCP servers are non-technical people who want to securely connect data sources to their AI application.

Hosted by Apple or not, but isn’t the biggest feature of iOS 27 LLM integration?

The biggest feature is stability, but Apple Intelligence has an excellent toolkit and API.

You mention RSS, but Substack is about paid subscribers, is it not? What do you think converts a Substack user to a subscriber; is it just a numbers game?

Do you feel the output could've been yours, or is it about the output feeling more humane?

I wish :) The style could have been mine, but it diverges quickly if context is too long.

Since I didnt write the content, my brain does not have the same ownership feeling.

I think the thought process, doing and undoing makes it yours, in this case we skip that part.

We're organized in small teams around specific products. That leads to mob programming being a good fit, so code reviews and knowledge sharing is organic. This gives us an opportunity to commit to main and do direct deploys to production. Treating every commit as deployable is key, but it drives good practices.

The largest benefit of mob programming (or software teaming or ensemble programming) is the continuous knowledge sharing. Instead of trying to figure out context during code reviews or syncs, you do it organically all the time. Developing together builds a tight team where people grow together.

Yeah, and reduces the lottery factor. Much less siloed knowledge banks creating unicorn Subject Matter Experts (SMEs). Lots of SMEs is a security risk.

Nice job! Pretty fun game.

Only improvement ideas I have are for a smoother start for new players:

1. Let the user start the game themselves so that they have a chance to read the rules without a stressful first impression.

2. Use a different label text than "Build your word here" as it sounds like a drag and drop target rather than an output.

I'd argue the value goes up with larger payloads. The tradeoff is ease of use vs efficiency.

Hence my question was about programming rather than engineering. Composition could, for a long time, be a task humans do whereas the components are generated by AI.

They're likely on the hype train, I'll give you that. Doesn't mean next generation won't be doing software engineering completely different from how it's done now.

Of course it will be different. It is different now than it was 10 years ago, even without AI, and it was another flavor of different 10 years before that. Jobs evolve. That doesn't mean that we should be advising people to not learn. Keep learning, and be comfortable adapting as things change.