One more thing to add is that the external communication code/infra is not written/managed by the agents and is part of a vetted distribution process.

I was also startled when I learned about the human ancestor who was the first to see a mirror.

The brilliance of AI is that it copies(mirrors) imperfectly and you can only look at part_of_the_copy(inference) at a time.

It seems it is true for gemini because they have a humongous sparse model but it isn't so true for the max performance opus-4.5/6 and gpt-5.2/3.

It is not about making it yourself but a tradeoff between how much it can be controlled and how much has seen the real world. Adding requirements learned by mistakes of others is slower in self-controlled development vs an open collaboration vs a company managing it. This is the reason vibe-coded(initial requirements) projects feels good to start but tough to evolve(with real learnings).

Vibe-coded projects are high-velocity but low-entropy. They start fast, but without the "real-world learnings" baked into collaborative projects, they often plateau as soon as the problem complexity exceeds the creator's immediate focus.

Microservices is bad for teams without discipline to implement "separation of concerns". They hope that physical network boundaries will force the discipline they couldn't maintain in a single codebase.

While microservices force physical separation, they don't stop "Spaghetti Architecture." Instead of messy code, you end up with "Distributed Spaghetti," where the dependencies are hidden in network calls and shared databases.

Microservices require more discipline in areas like:

Observability: Tracking a single request across 10 services. Consistency: Dealing with distributed transactions and eventual consistency. DevOps: Managing N deployment pipelines instead of one.

For most teams Modular monolith is often the better "first step." It enforces strict boundaries within a single deployment unit using language-level visibility (like private packages or modules). It gives you the "Separation of Concerns" without the "Distributed Spaghetti" network tax.

> Observability: Tracking a single request across 10 services

I'm not sure if this is a discipline issue in the way that domain driven design, say, is a discipline issue. If you instrument requests with a global ID and point at tool at it then you're basically done from the individual team perspective.

Uh, that's not my experience at all.

Sure you can say e.g "this property wasnt set in this request while being processed by this service managed by this team", but why it wasn't set will inevitably need multiple teams, each doing in-depth analysis how such as state could've been caused because they always inevitably become distributed monoliths - the former is being provided by the instrumentation, but the latter isn't (and even the former is not perfect, as not all frameworks/languages have equal support)

> and shared databases.

According to my understanding this is one of the reasons why microservices were invented, to prevent shared databases?

pydantic/pydanticAI in builder mode or llamaindex in solution architect mode.

AI/non-AI/human/hybrid: It doesn't matter which one is the writer.

It's the reader who decides how good the writing is.

The joy which the writer gets by being creative is of no consequence to the reader. Sacrifice of this joy to adopt emerging systems is immaterial.

Even thin single use plastic works. The first time I saw it it was surreal.

The thinner the better --- thermal conductivity is what keeps the temperature from rising too far.

So this is about customer support. Google supports by the customer by a better product but minimal manual support for issues later.

AWS has an organically evolved bad product which has been designed by long line of six page memos but a manual support in case things get too confusing or the customer just need emotional support.

I wanted to see how far it will go. I started with asking it to simple test app. It said it is a great idea. And asked me if I want to do market analysis. I came back later and asked it to do a TAM analysis. It said $2-20B. Then it asked if it can make a one page investor pitch. I said ok, go ahead. Then it asked if I want a detailed slide deck. After making the deck it asked if I want a keynote file for the deck.

All this while I was thinking this is more dangerous than instagram. Instagram only sent me to the gym and to touristic places and made me buy some plastic. ChatGPT wants me to be a tech bro and speed track the Billion dollar net worth.