theshrike79

Analogy: it’s fine to write stories for yourself mad libs style with AI

It’s not ok to write stories with AI and post them for others to read claiming “I did that”

Get the difference?

Similarly some of the molds for angentic work are reusable as long as you stay in the same general field.

We're not trying to perfectly define the problem, but rather adding barriers to so that the AI can't veer off course and drive itself down a cliff.

Especially if you're in a product house developing and improving a single product over years, creating the "mold" is even more important. You know where you've been and where you want to go so it's easier to define the technologies and systems the AI should use.

For greenfield stuff there are some parts that can be re-used between clients, but there's definitely less of it.

But I do agree that code is not the problem, defining and describing the problem is the problem =)

Nobody said the mold has to be done in a human language. It _can_ be a part of it for the fuzzy bits.

But it's just writing the hard limits on the outside, in code. Define that when A goes in B must come out. Enforce hard linting rules and other code-level checks on the output etc.

Not just specs and prompts, tests, actual procedural limits. No program will ever be perfect[0], but you need to get it good enough for the problem at hand.

A human defines the checks (the mold) that give the agent the limits. They can be TLA+ definitions, linters, cyclomatic complexity checkers, unit tests, integration tests, end to end tests etc. And usually some written docs - made in a way that's specifically targeted at agents. Those define the limits the agent has to stay inside of.

There will always be work for human QA too, an AI can't determine if something feels off in an app's flow, it has no taste or concept of usability beyond the purely mechanical rules.

[0] Not talking about health, aerospace or nuclear stuff here naturally.

Vibe coding the "feel" and flows of the app - if they know how to do it and what they want.

These are for highly specific stuff like a tool to help a copywriter work on game dialogue for example.

It's a fuckton faster for the actual expert in the field to do it than me first learning enough of their craft to know the terms and how they work to get there eventually.

The actual code that does anything meaningful is made by Actual Programmers. As well as everything beyond that, where it's run the CI pipelines, tests, infrastructure to run it etc.

It's like an architect asking a client to draw and describe their dream home and using it as a basis for the final product.

My main advice as a parent:

- The most important task of a parent is to make sure your child is bored as FUCK as often as possible.

BUT they should have the means to alleviate that boredom with something creative or interactive. Not just vegging out and consuming content, they should have as many opportunities to create or interact with things available to them.

This is how we figured out that our kid is a proper artist - despite both of their parents being unable to draw anything except technical drawings or UML charts. Boredom + available arts and crafts = fun.

Oh and get your kid reading, the current state of the world is that if your child can read AND UNDERSTAND what they read - not just recite the words out loud - they'll have a massive leg up compared to everyone else. Reading anything is better than nothing.

Comics or even subtitles on non-native programs are better than nothing.

How can I "fully own" the device I use to run 3rd party streaming apps?

Google PR is so good that people tend to forget that the vast majority of Google's income is from ads.

Compared to that, their hardware, SaaS, and other ventures are just 20% side projects.

So you've NEVER had a sketch, proof of concept or prototype end up being a part of the final product? Now you're stuck with a piece of crap that was implemented expecting to be thrown away, but then because of time and money constraints it's now a load-bearing (heh) part of the application.

It also takes more time for humans to build prototypes and PoCs than doing the same with an agent. Iteration speed and time-to-market matters more and more (case in point: mobile games).

I've came up with the same basic analogy as you.

What it boils down to is that the future of coding is more about creating the mold where the code is poured in and knowing how exact of a mold is "good enough" for the problem at hand.

When the mold is done, you let the agent pour in the code in any format you like. It can create a Swift version, Rust version and a web assembly version in "half a soda" as you put it =)

The people for whom the only enjoyment in programming was molding the perfect item from scratch will still be needed, but less and less as we get better and faster in defining the molds for the agent to pour the code in.

Before I had to dig specs of an application out of a client's mind and try to form them into software with a full-ass team. Now we can pretty much "just" give them Claude and teach them to describe what they want and iterate to get something that maybe resembles an MVP but in more cases is just an interactive UI spec we can use as a reference to build the actual tool.

Truly spoken as someone who has never worked with legacy code. You know, the kind that's still running Java 1.something when Java was already doing full numbered releases.

The kind that works, but everyone who knows why has left the company. The whole codebase is written in a way that makes automated testing either impossible or so time-consuming that the client will never pay for the required refactoring.

There is way too much code in the world we never were able to rewrite due to real-world concerns. There were people who had the skill, but a part of that skill came with knowing the risks of doing major refactoring to a money-generating system that is ancient, but still works.

Anecdote: I had to work with a system where the original coder (long gone) had rewritten Linked Lists with their custom solution that worked normally except the first X items were the sum, average and mean of the data. Fun times.

Without even knowing what it is, I'm kinda guessing Datadog's AI also has a nice hefty price tag attached to it?

And if not today, it will have one soon.

No need, I still have vibe coded stuff from the times before monthly plans for Claude and Codex over a year ago. I can jump into most of them and just start adding stuff without any major issues - they have better test coverage and CI than many projects at my day job :)

It's surprisingly easy to do that shit properly when budgets and time aren't an issue.