anditherobot

AI can generate what a company makes. Can it generate what a company is?

Producing artifacts: media, code, documents, the visible output has clearly gotten easier. But the other things, like knowing what's worth building in the first place and making the right judgment call, still seem to be left to the humans.

Microsoft’s biggest dev move would be to make one clear “default” stack for each app type: one for web, one for desktop, one for mobile.

They already have strong tools. Just way too many paths They should make the recommended stack obvious and well-supported.

I am experimenting with the post LLM Daily Workflow

Vibe coding sits on an axis from smart autocomplete to one-shotting a $1B SaaS. Traditional software engineering was about holding the system in your head and translating it into syntax, fighting tooling and architecture decisions along the way. I think done properly it removes many of these friction points along the way to validating / implementing the idea.

Now it's easier to traverse a live plan and to quickly make micro pivots as you go.

I also think that architecture needs to change. Design patterns that will help to provide as much context to the LLM as possible to increase understanding.

Fair challenge to the idea. But what i am saying is that every line of boilerplate, every import statement, every configuration file consumes precious tokens.

The more code, the more surface area the LLM needs to cover before understanding or implementing correctly.

Right now the solution to expensive token limits is the most token-efficient technology. let's reframe it better. Was react made to help humans organize code better or machines?

Is the High Code-to-Functionality Ratio 3 lines that do real work > 50 lines of setup really necessary?

We're overlooking a critical metric in AI-assisted development: Token and Context Window to Utility Ratio.

AI coding tools are burning massive token budgets on boilerplate thousands of tokens just to render simple interfaces.

Consider the token cost of "Hello World":

- Tkinter: `import tkinter as tk; tk.Button(text="Hello").pack()`

- React: 500MB of node_modules, and dependencies

Right now context windows token limits are finite and costly. What do you think?

My prediction is that tooling that manage token and context efficiency will become essential.

From punch cards to assembly, to C, to modern languages and web frameworks, each generation raised the abstraction. Agentic frameworks are the next one.

With Visual Studio and Copilot I like the fact that runs a comment and then can read the output back and then automatically continues based on the error message let's say there's a compilation error or a failed test case, It reads it and then feeds that back into the system automatically. Once the plan is satisfied, it marks it as completed

Have you tried Scoped context packages? Basically for each task, I create a .md file that includes relevant file paths, the purpose of the task, key dependencies, a clear plan of action, and a test strategy. It’s like a mini local design doc. I found that it helps ground implementation and stabilizes the output of the agents.

Does this mean a developer doesn't have to install nginx or iis ?

That's a very cool accomplishment.

What language did you use to write the code?

I also have another question, did you witness the transition from punched cards to terminals?

How did people differentiate between 1 and L, 5 and S, 0 and O?

ex: 1055 & LOSS ( one zero five five & loss)